WP10 · Draft web edition · as of 2026-10-30
Generative AI in apparel design and what a greenfield maker should adopt
Each weft is one exhibit's own data, normalised; each warp group is a chapter. The probe reads the exhibit's own value where it crosses. Procedural visualisation, not a measurement.
Operate the evidence first
The weft the probe was reading, lifted out of the cloth: the same exhibit at full size, with the probe as its cursor. Choose a weft, step through it, compare its series.
Read-out
Approximate inherited sector baseline from Cameroon Trade Hub (R06, publication date unrecorded) and stated 2030 national policy target from SND30 via Ecofin Agency (R07, publication date unrecorded). The 2030 column represents a national policy target rather than an achieved operating share or a forecast return from design software.
Unit: percent of cotton fibre. Status: sourced. Sources: R06, R07.
Read this exhibit in its chapter ↗Read-out
Illustrative GFT change-control workflow when a candidate fabric departs from the approved swatch envelope, routing back through pattern, fit, costing and release gates. Informed by S19, S20 and S22.
Unit: workflow steps. Status: illustrative. Sources: S19, S20, S22. Illustrative figures are teaching examples, not measured factory results.
Read this exhibit in its chapter ↗Illustrative GFT evaluation rubric weights (each row sums to 100 percent) grounded in NIST AI RMF contextual measurement (S19) and TailorCoPilot quality dimensions (sewability, structural balance, reference conformity and workload in S15, S1005). Completion time receives at most 10 percent weight and is scored only after critical defect count equals zero. No trainee results are fabricated.
Read-out
Illustrative GFT evaluation rubric weights (each row sums to 100 percent) grounded in NIST AI RMF contextual measurement (S19) and TailorCoPilot quality dimensions (sewability, structural balance, reference conformity and workload in S15, S1005). Completion time receives at most 10 percent weight and is scored only after critical defect count equals zero. No trainee results are fabricated.
Unit: illustrative rubric weight (percent of 100 per task). Status: illustrative. Sources: S15, S19. Illustrative figures are teaching examples, not measured factory results.
Read this exhibit in its chapter ↗Read-out
GFT proposed sequence. Prerequisites include authorised inputs, approved blocks, material records, technicians and a frozen protocol. Baseline and assisted work use matched conditions. Physical checks and receiving-CAD readback depend on suitable candidates. Numeric positions show order only; team capacity, durations and calendar dates are unknown. Review can stop, repair or bound expansion.
Unit: illustrative dependency positions, not elapsed time. Status: illustrative. Sources: S19, S20, S22. Illustrative figures are teaching examples, not measured factory results.
Read this exhibit in its chapter ↗The paper's argument
Chapter read-out · hover or focus a thread
Greenfield apparel sponsors and plant leadership, Designers, pattern technicians and product-development leads, Quality, procurement and digital-system teams, Technical partners assessing a bounded generative-design pilot
0127 min · 4 exhibits
A convincing image cannot authorise a cutting order
GFT should buy creative assistance selectively and release garments only through an accountable specification process.
01 / 05The thesis
A greenfield apparel maker should adopt generative design only within a measured, technician-led specification workflow that preserves material, fit, rights and release evidence, while treating research progress as a reason to test rather than proof of production readiness.
14 chapters · 4 parts · 361 minutes
Prepared for: Greenfield apparel sponsors and plant leadership, Designers, pattern technicians and product-development leads, Quality, procurement and digital-system teams, Technical partners assessing a bounded generative-design pilot
02 / 05Part I · Production readiness is the test
Generative AI can broaden apparel design exploration, but a convincing image is not an instruction to cut fabric. This paper examines research published from 2023 to October 2026 and asks what a greenfield maker should adopt, under what conditions, and with whose approval. It distinguishes image ideation, structured sewing-pattern generation, material estimation, fit-aware evaluation and production release.
Part I · chapters 01 to 03 · 80 minutes · 12 exhibits
03 / 05Part II · Specifications require geometry, materials and fit
Parametric garment research existed in 2023; later multimodal and agentic systems extend the available methods without establishing universal factory readiness. The paper argues for an accountable handoff from a constrained brief to editable geometry, measured material inputs, fit checks, a controlled tech pack and receiving-CAD readback.
Part II · chapters 04 to 08 · 130 minutes · 22 exhibits
04 / 05Part III · Adoption requires people, rights and measured economics
It separates research results from vendor documentation and from proposed GFT acceptance conditions. A running cotton-shirt example makes the decisions concrete without inventing an engagement, buyer or operating result. Rights review, cultural engagement, technician development and model-version control form part of the workflow rather than an afterthought.
Part III · chapters 09 to 12 · 101 minutes · 17 exhibits
05 / 05Part IV · GFT should scale only what passes its gates
An explicitly illustrative sampling-cost model shows how review effort and retained physical checks can change the economic case. The closing roadmap aligns with GFT's Cameroon textile programme: establish records and operating measurement first, then qualify a bounded partnered generative-specification pilot. Adoption remains conditional on local evidence. Nothing in the paper constitutes investment, legal or tax advice.
Part IV · chapters 13 to 14 · 50 minutes · 8 exhibits
The cloth seen from above
Weaving draft · 14 chapters × 59 exhibits
One column per chapter, one knot per exhibit; the glyph is its type family, as on the chips above. Select a knot to open the exhibit below.
Exhibit 01 · chapter 01 · Stacked composition
Read-out
Approximate inherited sector baseline from Cameroon Trade Hub (R06, publication date unrecorded) and stated 2030 national policy target from SND30 via Ecofin Agency (R07, publication date unrecorded). The 2030 column represents a national policy target rather than an achieved operating share or a forecast return from design software.
Unit: percent of cotton fibre. Status: sourced. Sources: R06, R07.
Read this exhibit in its chapter ↗Read-out
Interlude · findings against chapters
The useful adoption unit is an accepted specification, not the number of generated images.S09S22S19
Structured sewing-pattern research already existed in 2023, so a simple image-only-to-pattern chronology is misleading.S02S03
Programs, pattern tokens, parameter JSON and schema-aware representations expose different technical control points.S08S09S10S14S16
A strong seam-relation metric is compatible with a substantially lower whole-garment digital assembly result.S12
Visual fabric generation and material-property inference do not replace physical material evidence.S01S11S28S32
Appearance-based virtual try-on cannot be assumed to establish size-correct fit.S13S27
Documented DXF support does not remove the need to verify units, grading, notches and allowances in the receiving workflow.S22
Commercial tool permission, human contribution and cultural permission answer distinct questions.S31S21S23S24
Economic and environmental benefits remain unproven until accepted outcomes and all changed costs or resource flows are measured.S19S29S25
GFT should preserve its staged programme and treat generative specification as a bounded partner pilot with stop conditions.S19S20
Cell strength is the recurrence of each finding's key terms in each chapter's text, computed from this web edition and scaled to the strongest chapter. It is a reading guide, not a citation.
Evidence stays attached
Every knot on the edge is one of the 203 records the chapters cite, sorted by grade. The counters filter them; select a record to read it and to light the chapters that cite it. A grade describes the supplied evidence record, not independent validation by the website; missing references are excluded.
All 203 records shown
c01-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
While the AI RMF can be used to prioritize risk, it does not prescribe risk tolerance.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Contextual evaluation and explicit organisational risk tolerance are required when governing AI systems.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
The NIST Generative AI Profile outlines voluntary actions for content provenance, empirical capability evaluation, source verification and lifecycle monitoring.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S21 · Grade A
Copyright Office Releases Part 2 of Artificial Intelligence Report
In the United States copyright context, human expressive control is distinguished from merely supplying text prompts to a generative model.
2025-01-29. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S23 · Grade A
Indigenous Peoples and Fashion
Fashion references to traditional cultural expressions require context-sensitive, respectful engagement with custodian communities rather than informal copying.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S24 · Grade A
Traditional Cultural Expressions
Traditional cultural expressions embody community identity and know-how; legal and ethical protection depends on jurisdiction and context.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
While the AI RMF can be used to prioritize risk, it does not prescribe risk tolerance.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
While the AI RMF can be used to prioritize risk, it does not prescribe risk tolerance.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
While the AI RMF can be used to prioritize risk, it does not prescribe risk tolerance.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
While the AI RMF can be used to prioritize risk, it does not prescribe risk tolerance.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
While the AI RMF can be used to prioritize risk, it does not prescribe risk tolerance.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S21 · Grade A
Copyright Office Releases Part 2 of Artificial Intelligence Report
It concludes that the outputs of generative AI can be protected by copyright only where a human author has determined sufficient expressive elements.
2025-01-29. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S25 · Grade A
Sustainable and Circular Textiles Strategy
The strategy looks at the entire lifecycle of textile products and proposes coordinated action to change how we produce and consume textiles.
2022-03-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
While the AI RMF can be used to prioritize risk, it does not prescribe risk tolerance.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
While the AI RMF can be used to prioritize risk, it does not prescribe risk tolerance.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S21 · Grade A
Copyright Office Releases Part 2 of Artificial Intelligence Report
It concludes that the outputs of generative AI can be protected by copyright only where a human author has determined sufficient expressive elements.
2025-01-29. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
While the AI RMF can be used to prioritize risk, it does not prescribe risk tolerance.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S21 · Grade A
Copyright Office Releases Part 2 of Artificial Intelligence Report
It concludes that the outputs of generative AI can be protected by copyright only where a human author has determined sufficient expressive elements.
2025-01-29. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S23 · Grade A
Indigenous Peoples and Fashion
WIPO aims to create opportunities for a dialogue between Indigenous Peoples and fashion companies to shape fair and equitable interaction between them.
2023-11-02. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S24 · Grade A
Traditional Cultural Expressions
TCEs are integral to the cultural and social identities of indigenous and local communities, embody know-how and skills, and transmit core values and beliefs.
n.d.. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S1101 · Grade A
Copyright Office Launches New Artificial Intelligence Initiative
The guidance makes clear that applicants have a duty to disclose the inclusion of AI-generated content in works submitted for registration.
2023-03-16. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S1102 · Grade A
Government launches public consultation on enhancing Copyright Ordinance regarding protection for artificial intelligence technology development
Under the existing CO, works generated by generative AI (AI-generated works) are already protected by copyright.
2024-07-08. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
While the AI RMF can be used to prioritize risk, it does not prescribe risk tolerance.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S25 · Grade A
Sustainable and Circular Textiles Strategy
The strategy looks at the entire lifecycle of textile products and proposes coordinated action to change how we produce and consume textiles.
2022-03-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
While the AI RMF can be used to prioritize risk, it does not prescribe risk tolerance.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S19 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
While the AI RMF can be used to prioritize risk, it does not prescribe risk tolerance.
2023-01-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S20 · Grade A
Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile
This document defines risks that are novel to or exacerbated by the use of GAI.
2024-07-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S01 · Grade B
Transforming Fashion with AI: A Comparative Study of Large Language Models in Apparel Design
However, our results indicate that Deepseek faced significant challenges in generating and recognizing fabric images.
2025-09-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S02 · Grade B
GarmentCode: Programming Parametric Sewing Patterns
Realistic representation of garments with valid sewing patterns is key to their accurate digital simulation and eventual fabrication.
2023-06-06. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S09 · Grade B
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Sewing patterns, the essential blueprints for fabric cutting and tailoring, act as a crucial bridge between design concepts and producible garments.
2024-12-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S10 · Grade B
ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
These sewing patterns can then be draped on a 3D body and animated.
2024-12-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S12 · Grade B
AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks
AutoSew achieves 96% F1-score and successfully assembles 73.3% of test garments without error, outperforming existing methods while relying solely on geometric input.
2026-02-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S13 · Grade B
FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On
Consequently, current VTO methods default to generating well-fitted results regardless of the garment or person size.
2026-04-09. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S17 · Grade B
EasyFashion: A Human-AI Co-Creation System for Personalized Fashion Design and Sewing Pattern Generation
Recent generative artificial intelligence (AI) systems can visualize garment ideas but often stop short of supporting downstream production.
2026-09-16. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S26 · Grade B
IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Design
This paper presents IMAGGarment, a fine-grained garment generation (FGG) framework that enables high-fidelity garment synthesis with precise control over silhouette, color, and logo placement.
2025-04-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S27 · Grade B
EASE: Parametric garment design with explicit and local ease control
Garment fit and comfort depend critically on ease, the local allowance of excess material relative to the body.
2026-06-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S30 · Grade B
GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns
For each generation step, we implement quality control conditions to exclude bad samples from the data.
2024-05-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S0101 · Grade B
GarmentDiffusion: 3D Garment Sewing Pattern Generation with Multimodal Diffusion Transformers
Garment sewing patterns are fundamental design elements that bridge the gap between design concepts and practical manufacturing.
2025-04-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S0102 · Grade B
GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling
Realistic digital garment modeling remains a labor-intensive task due to the intricate process of translating 2D sewing patterns into high-fidelity, simulation-ready 3D garments.
2025-04-02. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S02 · Grade B
GarmentCode: Programming Parametric Sewing Patterns
Realistic representation of garments with valid sewing patterns is key to their accurate digital simulation and eventual fabrication.
2023-06-06. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S03 · Grade B
Towards Garment Sewing Pattern Reconstruction from a Single Image
Then, we propose a two-level Transformer network called Sewformer, which significantly improves the sewing pattern prediction performance.
2023-11-07. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S04 · Grade B
DressCode: Autoregressively Sewing and Generating Garments from Text Guidance
We first introduce SewingGPT, a GPT-based architecture integrating cross-attention with text-conditioned embedding to generate sewing patterns with text guidance.
2024-01-29. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S05 · Grade B
Garment3DGen: 3D Garment Stylization and Texture Generation
The generated assets can be directly draped and simulated on human bodies.
2024-03-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S07 · Grade B
HAIGEN: Towards Human-AI Collaboration for Facilitating Creativity and Style Generation in Fashion Design
Specifically, HAIGEN consists of four modules.
2024-08-01. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S08 · Grade B
AIpparel: A Multimodal Foundation Model for Digital Garments
To simplify this process, we introduce AIpparel, a multimodal foundation model for generating and editing sewing patterns.
2024-12-05. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S09 · Grade B
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Sewing patterns, the essential blueprints for fabric cutting and tailoring, act as a crucial bridge between design concepts and producible garments.
2024-12-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S10 · Grade B
ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
These sewing patterns can then be draped on a 3D body and animated.
2024-12-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S11 · Grade B
Image2Garment: Simulation-ready Garment Generation from a Single Image
Our approach introduces two new datasets (FTAG and T2P) and delivers simulation-ready garments from a single image without iterative optimization.
2026-01-14. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S13 · Grade B
FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On
Consequently, current VTO methods default to generating well-fitted results regardless of the garment or person size.
2026-04-09. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S14 · Grade B
PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments
PatternGSL preserves the physical rigor of pattern-based models while removing template dependence, elevating sewing structure as a first-class target for generative modeling.
2026-06-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S16 · Grade B
GarmentWeaver: Schema-Aware Structured Synthesis for Multimodal Sewing Patterns
In this paper, we present GarmentWeaver, a schema-aware framework for multimodal Sewing pattern generation.
2026-08-31. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S18 · Grade B
Inverse Garment Design with Visual Agents
Carefully designed tools and an evolving memory make this refinement converge on the target geometry.
2026-10-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S27 · Grade B
EASE: Parametric garment design with explicit and local ease control
Garment fit and comfort depend critically on ease, the local allowance of excess material relative to the body.
2026-06-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S01 · Grade B
Transforming Fashion with AI: A Comparative Study of Large Language Models in Apparel Design
A comparative LLM study on a custom dataset reports approximate 80 percent base-construction and 55 percent detailed-construction fabric classification accuracy for its top-performing tested setup, alongside persistent difficulty recognising intricate fabric structures from images.
2025-09-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S02 · Grade B
GarmentCode: Programming Parametric Sewing Patterns
Component-based parametric sewing-pattern programs separate high-level design choices from low-level panel geometry.
2023-06-06. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S04 · Grade B
DressCode: Autoregressively Sewing and Generating Garments from Text Guidance
Text-guided sewing-pattern generation and physically based rendering textures are separated into distinct branches for computer-graphics assets.
2024-01-29. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S07 · Grade B
HAIGEN: Towards Human-AI Collaboration for Facilitating Creativity and Style Generation in Fashion Design
A human-AI fashion ideation architecture combines cloud inspiration generation with local sketch-library, style-recommendation and colouring modules; v4 revised 2026-07-27.
2024-08-01. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S09 · Grade B
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Multimodal design inputs such as sketches, images and text are translated into parametric pattern-making programs; v3 revised 2025-04-09.
2024-12-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S10 · Grade B
ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
A vision-language model emits JSON garment descriptions and continuous parameters that drive a parametric sewing-pattern program through interactive dialogue; v3 revised 2025-04-03.
2024-12-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S13 · Grade B
FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On
Appearance-driven virtual try-on methods can synthesis well-fitted visuals even when body and garment sizes mismatch.
2026-04-09. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S26 · Grade B
IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Design
Multi-condition appearance synthesis separates global silhouette and colour control from local detail and logo placement; v2 revised 2025-09-08.
2025-04-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S0301 · Grade B
GarmentSketch: Large-scale Sketch-to-Fashion Benchmark
A benchmark of 26,249 fashion sketches across 21 garment categories paired with MLLM captions refined by humans demonstrates both utility and current limitations in sketch-guided generation.
2026-06-12. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S0302 · Grade B
Fine-Grained Controllable Apparel Showcase Image Generation via Garment-Centric Outpainting
Garment-centric outpainting preserves an existing segmented garment image while generating showcase poses and model appearance around it, illustrating that marketing showcase synthesis and garment construction design are distinct tasks.
2025-03-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S02 · Grade B
GarmentCode: Programming Parametric Sewing Patterns
Realistic representation of garments with valid sewing patterns is key to their accurate digital simulation and eventual fabrication.
2023-06-06. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S03 · Grade B
Towards Garment Sewing Pattern Reconstruction from a Single Image
Then, we propose a two-level Transformer network called Sewformer, which significantly improves the sewing pattern prediction performance.
2023-11-07. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S04 · Grade B
DressCode: Autoregressively Sewing and Generating Garments from Text Guidance
We first introduce SewingGPT, a GPT-based architecture integrating cross-attention with text-conditioned embedding to generate sewing patterns with text guidance.
2024-01-29. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S08 · Grade B
AIpparel: A Multimodal Foundation Model for Digital Garments
To simplify this process, we introduce AIpparel, a multimodal foundation model for generating and editing sewing patterns.
2024-12-05. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S09 · Grade B
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Sewing patterns, the essential blueprints for fabric cutting and tailoring, act as a crucial bridge between design concepts and producible garments.
2024-12-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S10 · Grade B
ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
These sewing patterns can then be draped on a 3D body and animated.
2024-12-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S12 · Grade B
AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks
AutoSew achieves 96% F1-score and successfully assembles 73.3% of test garments without error, outperforming existing methods while relying solely on geometric input.
2026-02-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S14 · Grade B
PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments
PatternGSL preserves the physical rigor of pattern-based models while removing template dependence, elevating sewing structure as a first-class target for generative modeling.
2026-06-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S15 · Grade B
TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking
Ultimately, TailorCoPilot demonstrates a viable pathway to capture practice-based expertise, operationalizing it to support both generative AI advancements and human apprenticeship.
2026-08-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S16 · Grade B
GarmentWeaver: Schema-Aware Structured Synthesis for Multimodal Sewing Patterns
In this paper, we present GarmentWeaver, a schema-aware framework for multimodal Sewing pattern generation.
2026-08-31. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S17 · Grade B
EasyFashion: A Human-AI Co-Creation System for Personalized Fashion Design and Sewing Pattern Generation
Recent generative artificial intelligence (AI) systems can visualize garment ideas but often stop short of supporting downstream production.
2026-09-16. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S18 · Grade B
Inverse Garment Design with Visual Agents
Carefully designed tools and an evolving memory make this refinement converge on the target geometry.
2026-10-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S27 · Grade B
EASE: Parametric garment design with explicit and local ease control
Garment fit and comfort depend critically on ease, the local allowance of excess material relative to the body.
2026-06-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S30 · Grade B
GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns
For each generation step, we implement quality control conditions to exclude bad samples from the data.
2024-05-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S0401 · Grade B
Generating Datasets of 3D Garments with Sewing Patterns
With this pipeline, we created the first large-scale synthetic dataset of 3D garment models with their sewing patterns.
2021-09-12. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S0402 · Grade B
NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments
We propose to use a garment sewing pattern, a realistic and compact garment descriptor, to facilitate the intrinsic garment shape estimation.
2022-01-31. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S0403 · Grade B
ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns
Their 2D shape is defined by a Signed Distance Function and 3D shape by a 2D to 3D mapping.
2023-05-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S0404 · Grade B
Learning Sewing Patterns via Latent Flow Matching of Implicit Fields
Despite progress in automated pattern generation, accurately modeling sewing patterns remains difficult due to the broad variability in panel geometry and seam arrangements.
2026-01-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S06 · Grade B
ContourCraft: Learning to Resolve Intersections in Neural Multi-Garment Simulations
However, handling collisions and intersections in neural simulations remains a largely unsolved problem.
2024-05-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S12 · Grade B
AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks
AutoSew achieves 96% F1-score and successfully assembles 73.3% of test garments without error, outperforming existing methods while relying solely on geometric input.
2026-02-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S14 · Grade B
PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments
PatternGSL preserves the physical rigor of pattern-based models while removing template dependence, elevating sewing structure as a first-class target for generative modeling.
2026-06-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S18 · Grade B
Inverse Garment Design with Visual Agents
Carefully designed tools and an evolving memory make this refinement converge on the target geometry.
2026-10-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S01 · Grade B
Transforming Fashion with AI: A Comparative Study of Large Language Models in Apparel Design
However, our results indicate that Deepseek faced significant challenges in generating and recognizing fabric images.
2025-09-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S02 · Grade B
GarmentCode: Programming Parametric Sewing Patterns
Realistic representation of garments with valid sewing patterns is key to their accurate digital simulation and eventual fabrication.
2023-06-06. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S05 · Grade B
Garment3DGen: 3D Garment Stylization and Texture Generation
The generated assets can be directly draped and simulated on human bodies.
2024-03-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S06 · Grade B
ContourCraft: Learning to Resolve Intersections in Neural Multi-Garment Simulations
However, handling collisions and intersections in neural simulations remains a largely unsolved problem.
2024-05-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S09 · Grade B
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Sewing patterns, the essential blueprints for fabric cutting and tailoring, act as a crucial bridge between design concepts and producible garments.
2024-12-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S10 · Grade B
ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
These sewing patterns can then be draped on a 3D body and animated.
2024-12-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S11 · Grade B
Image2Garment: Simulation-ready Garment Generation from a Single Image
Our approach introduces two new datasets (FTAG and T2P) and delivers simulation-ready garments from a single image without iterative optimization.
2026-01-14. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S12 · Grade B
AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks
AutoSew achieves 96% F1-score and successfully assembles 73.3% of test garments without error, outperforming existing methods while relying solely on geometric input.
2026-02-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S14 · Grade B
PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments
PatternGSL preserves the physical rigor of pattern-based models while removing template dependence, elevating sewing structure as a first-class target for generative modeling.
2026-06-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S18 · Grade B
Inverse Garment Design with Visual Agents
Carefully designed tools and an evolving memory make this refinement converge on the target geometry.
2026-10-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S27 · Grade B
EASE: Parametric garment design with explicit and local ease control
Garment fit and comfort depend critically on ease, the local allowance of excess material relative to the body.
2026-06-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S28 · Grade B
OmniFabric: Coherent UV Space Texture Synthesis for 3D Garment Reconstruction
While recent generative models have significantly advanced 3D geometry reconstruction, synthesizing high-quality textures remains a bottleneck.
2026-09-24. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S29 · Grade B
Product Standard
Product rules offer more specification for a given product category than the general standard can provide.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S30 · Grade B
GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns
For each generation step, we implement quality control conditions to exclude bad samples from the data.
2024-05-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S0601 · Grade B
How Will It Drape Like? Capturing Fabric Mechanics from Depth Images
We propose a method to estimate the mechanical parameters of fabrics using a casual capture setup with a depth camera.
2023-04-13. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S0602 · Grade B
Learnable Persistent Wrinkle Formation in Cloth Simulation
We introduce Fabric-101, an inclusive, accurate, and extendable fabric dataset comprising over 101 common fabrics following textile standards.
2026-09-12. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S13 · Grade B
FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On
Consequently, current VTO methods default to generating well-fitted results regardless of the garment or person size.
2026-04-09. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S27 · Grade B
EASE: Parametric garment design with explicit and local ease control
Garment fit and comfort depend critically on ease, the local allowance of excess material relative to the body.
2026-06-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S30 · Grade B
GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns
For each generation step, we implement quality control conditions to exclude bad samples from the data.
2024-05-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S02 · Grade B
GarmentCode: Programming Parametric Sewing Patterns
Realistic representation of garments with valid sewing patterns is key to their accurate digital simulation and eventual fabrication.
2023-06-06. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S04 · Grade B
DressCode: Autoregressively Sewing and Generating Garments from Text Guidance
We first introduce SewingGPT, a GPT-based architecture integrating cross-attention with text-conditioned embedding to generate sewing patterns with text guidance.
2024-01-29. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S09 · Grade B
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Sewing patterns, the essential blueprints for fabric cutting and tailoring, act as a crucial bridge between design concepts and producible garments.
2024-12-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S12 · Grade B
AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks
AutoSew achieves 96% F1-score and successfully assembles 73.3% of test garments without error, outperforming existing methods while relying solely on geometric input.
2026-02-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S14 · Grade B
PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments
PatternGSL preserves the physical rigor of pattern-based models while removing template dependence, elevating sewing structure as a first-class target for generative modeling.
2026-06-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S15 · Grade B
TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking
Ultimately, TailorCoPilot demonstrates a viable pathway to capture practice-based expertise, operationalizing it to support both generative AI advancements and human apprenticeship.
2026-08-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S23 · Grade B
Indigenous Peoples and Fashion
WIPO aims to create opportunities for a dialogue between Indigenous Peoples and fashion companies to shape fair and equitable interaction between them.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S24 · Grade B
Traditional Cultural Expressions
TCEs are integral to the cultural and social identities of indigenous and local communities, embody know-how and skills, and transmit core values and beliefs.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S26 · Grade B
IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Design
This paper presents IMAGGarment, a fine-grained garment generation (FGG) framework that enables high-fidelity garment synthesis with precise control over silhouette, color, and logo placement.
2025-04-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S28 · Grade B
OmniFabric: Coherent UV Space Texture Synthesis for 3D Garment Reconstruction
While recent generative models have significantly advanced 3D geometry reconstruction, synthesizing high-quality textures remains a bottleneck.
2026-09-24. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S0801 · Grade B
TexTile: A Differentiable Metric for Texture Tileability
Existing methods for tileable texture synthesis focus on general texture quality, but lack explicit analysis of the intrinsic repeatability properties of a texture.
2024-03-19. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S0802 · Grade B
FabricDiffusion: High-Fidelity Texture Transfer for 3D Garments Generation from In-The-Wild Clothing Images
We show that FabricDiffusion can transfer various features from a single clothing image including texture patterns, material properties, and detailed prints and logos.
2024-10-02. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S0803 · Grade B
Structured Pattern Expansion with Diffusion Models
In this paper, we address the synthesis of structured, stationary patterns, where diffusion models are generally less reliable and, more importantly, less controllable.
2024-11-12. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S0804 · Grade B
Content Credentials: C2PA Technical Specification 2.1
Each time an asset is changed, the existing provenance of the asset is preserved, with each new change being added to the provenance.
2024-09. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S10 · Grade B
ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
These sewing patterns can then be draped on a 3D body and animated.
2024-12-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S15 · Grade B
TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking
Ultimately, TailorCoPilot demonstrates a viable pathway to capture practice-based expertise, operationalizing it to support both generative AI advancements and human apprenticeship.
2026-08-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S01 · Grade B
Transforming Fashion with AI: A Comparative Study of Large Language Models in Apparel Design
However, our results indicate that Deepseek faced significant challenges in generating and recognizing fabric images.
2025-09-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S02 · Grade B
GarmentCode: Programming Parametric Sewing Patterns
Realistic representation of garments with valid sewing patterns is key to their accurate digital simulation and eventual fabrication.
2023-06-06. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S07 · Grade B
HAIGEN: Towards Human-AI Collaboration for Facilitating Creativity and Style Generation in Fashion Design
Specifically, HAIGEN consists of four modules.
2024-08-01. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S08 · Grade B
AIpparel: A Multimodal Foundation Model for Digital Garments
To simplify this process, we introduce AIpparel, a multimodal foundation model for generating and editing sewing patterns.
2024-12-05. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S09 · Grade B
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Sewing patterns, the essential blueprints for fabric cutting and tailoring, act as a crucial bridge between design concepts and producible garments.
2024-12-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S10 · Grade B
ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
These sewing patterns can then be draped on a 3D body and animated.
2024-12-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S11 · Grade B
Image2Garment: Simulation-ready Garment Generation from a Single Image
Our approach introduces two new datasets (FTAG and T2P) and delivers simulation-ready garments from a single image without iterative optimization.
2026-01-14. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S12 · Grade B
AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks
AutoSew achieves 96% F1-score and successfully assembles 73.3% of test garments without error, outperforming existing methods while relying solely on geometric input.
2026-02-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S13 · Grade B
FIT: A Large-Scale Dataset for Fit-Aware Virtual Try-On
Consequently, current VTO methods default to generating well-fitted results regardless of the garment or person size.
2026-04-09. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S14 · Grade B
PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments
PatternGSL preserves the physical rigor of pattern-based models while removing template dependence, elevating sewing structure as a first-class target for generative modeling.
2026-06-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S15 · Grade B
TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking
Ultimately, TailorCoPilot demonstrates a viable pathway to capture practice-based expertise, operationalizing it to support both generative AI advancements and human apprenticeship.
2026-08-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S16 · Grade B
GarmentWeaver: Schema-Aware Structured Synthesis for Multimodal Sewing Patterns
In this paper, we present GarmentWeaver, a schema-aware framework for multimodal Sewing pattern generation.
2026-08-31. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S18 · Grade B
Inverse Garment Design with Visual Agents
Carefully designed tools and an evolving memory make this refinement converge on the target geometry.
2026-10-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S23 · Grade B
Indigenous Peoples and Fashion
WIPO aims to create opportunities for a dialogue between Indigenous Peoples and fashion companies to shape fair and equitable interaction between them.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S26 · Grade B
IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Design
This paper presents IMAGGarment, a fine-grained garment generation (FGG) framework that enables high-fidelity garment synthesis with precise control over silhouette, color, and logo placement.
2025-04-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S27 · Grade B
EASE: Parametric garment design with explicit and local ease control
Garment fit and comfort depend critically on ease, the local allowance of excess material relative to the body.
2026-06-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S30 · Grade B
GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns
For each generation step, we implement quality control conditions to exclude bad samples from the data.
2024-05-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S1001 · Grade B
The Metacognitive Demands and Opportunities of Generative AI
Generative AI (GenAI) systems offer unprecedented opportunities for transforming professional and personal work, yet present challenges around prompting, evaluating and relying on outputs, and optimizing workflows.
2023-12-18. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S1002 · Grade B
Explanations Can Reduce Overreliance on AI Systems During Decision-Making
Our results suggest that some of the null effects found in literature could be due in part to the explanation not sufficiently reducing the costs of verifying the AI's prediction.
2022-12-13. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S1003 · Grade B
NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments
Our experiments show that NeuralTailor successfully reconstructs sewing patterns and generalizes to garment types with pattern topologies unseen during training.
2022-01-31. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S1004 · Grade B
Aligning Constraint Generation with Design Intent in Parametric CAD
For a design to be easily editable, the constraints must effectively capture design intent, ensuring the geometry updates predictably when parameters change.
2025-04-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S1005 · Grade B
TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking (v3 HTML full text)
Although the results suggest that trace-based support improves revision performance and usability, we do not yet know whether these benefits translate into durable learning or long-term skill development.
2026-08-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S07 · Grade B
HAIGEN: Towards Human-AI Collaboration for Facilitating Creativity and Style Generation in Fashion Design
Specifically, HAIGEN consists of four modules.
2024-08-01. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S09 · Grade B
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Sewing patterns, the essential blueprints for fabric cutting and tailoring, act as a crucial bridge between design concepts and producible garments.
2024-12-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S10 · Grade B
ChatGarment: Garment Estimation, Generation and Editing via Large Language Models
These sewing patterns can then be draped on a 3D body and animated.
2024-12-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S12 · Grade B
AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks
AutoSew achieves 96% F1-score and successfully assembles 73.3% of test garments without error, outperforming existing methods while relying solely on geometric input.
2026-02-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S15 · Grade B
TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking
Ultimately, TailorCoPilot demonstrates a viable pathway to capture practice-based expertise, operationalizing it to support both generative AI advancements and human apprenticeship.
2026-08-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S30 · Grade B
GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns
For each generation step, we implement quality control conditions to exclude bad samples from the data.
2024-05-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S1103 · Grade B
Content Credentials: C2PA Technical Specification 2.1
Each time an asset is changed, the existing provenance of the asset is preserved, with each new change being added to the provenance.
2024-09. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S15 · Grade B
TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking
Ultimately, TailorCoPilot demonstrates a viable pathway to capture practice-based expertise, operationalizing it to support both generative AI advancements and human apprenticeship.
2026-08-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S29 · Grade B
Product Standard
The Product Standard can be used to understand the full life cycle emissions of a product and focus efforts on the greatest GHG reduction opportunities.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S09 · Grade B
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Sewing patterns, the essential blueprints for fabric cutting and tailoring, act as a crucial bridge between design concepts and producible garments.
2024-12-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S15 · Grade B
TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking
Ultimately, TailorCoPilot demonstrates a viable pathway to capture practice-based expertise, operationalizing it to support both generative AI advancements and human apprenticeship.
2026-08-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S30 · Grade B
GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns
For each generation step, we implement quality control conditions to exclude bad samples from the data.
2024-05-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S09 · Grade B
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
Sewing patterns, the essential blueprints for fabric cutting and tailoring, act as a crucial bridge between design concepts and producible garments.
2024-12-11. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S15 · Grade B
TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking
Ultimately, TailorCoPilot demonstrates a viable pathway to capture practice-based expertise, operationalizing it to support both generative AI advancements and human apprenticeship.
2026-08-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S30 · Grade B
GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns
For each generation step, we implement quality control conditions to exclude bad samples from the data.
2024-05-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗R27 · Grade B · inherited record
Inherited evidence R27
AI at scale in fashion: inventory cost down 35 to 40 percent; forecast accuracy up 20 to 30 percent; revenue per customer up 15 to 25 percent; forecast errors cut 20 to 50 percent; lost sales down up to 65 percent; 75 percent of executives prioritising; sector operating-profit potential US$150 to 275 billion over three to five years.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
c01-S22 · Grade C
2D Pattern (DXF) Import/Export
DXF is a standard file format of industrial CAD patterns and stores 2D pattern information.
2026-07-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S22 · Grade C
2D Pattern (DXF) Import/Export
DXF is a standard file format of industrial CAD patterns and stores 2D pattern information.
2026-07-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S31 · Grade C
Adobe Firefly FAQ
For features without the beta label, you can use Firefly-generated outputs in your commercial projects.
2026-05-13. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S22 · Grade C
2D Pattern (DXF) Import/Export
DXF is a standard file format of industrial CAD patterns and stores 2D pattern information.
2026-07-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S22 · Grade C
2D Pattern (DXF) Import/Export
DXF is a standard file format of industrial CAD patterns and stores 2D pattern information.
2026-07-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S32 · Grade C
Creating 3D Fabric
You must enter the weight and thickness of the fabric in the Description.
2025-04-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S22 · Grade C
2D Pattern (DXF) Import/Export
DXF is a standard file format of industrial CAD patterns and stores 2D pattern information.
2026-07-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S22 · Grade C
2D Pattern (DXF) Import/Export
DXF is a standard file format of industrial CAD patterns and stores 2D pattern information.
2026-07-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S31 · Grade C
Adobe Firefly FAQ
For features without the beta label, you can use Firefly-generated outputs in your commercial projects.
2026-05-13. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S32 · Grade C
Creating 3D Fabric
You must enter the weight and thickness of the fabric in the Description.
2025-04-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S22 · Grade C
2D Pattern (DXF) Import/Export
DXF is a standard file format of industrial CAD patterns and stores 2D pattern information.
2026-07-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S32 · Grade C
Creating 3D Fabric
You must enter the weight and thickness of the fabric in the Description.
2025-04-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S22 · Grade C
2D Pattern (DXF) Import/Export
DXF is a standard file format of industrial CAD patterns and stores 2D pattern information.
2026-07-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S32 · Grade C
Creating 3D Fabric
You must enter the weight and thickness of the fabric in the Description.
2025-04-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S22 · Grade C
2D Pattern (DXF) Import/Export
DXF is a standard file format of industrial CAD patterns and stores 2D pattern information.
2026-07-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S31 · Grade C
Adobe Firefly FAQ
For features without the beta label, you can use Firefly-generated outputs in your commercial projects.
2026-05-13. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S32 · Grade C
Creating 3D Fabric
You must enter the weight and thickness of the fabric in the Description.
2025-04-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S22 · Grade C
2D Pattern (DXF) Import/Export
DXF is a standard file format of industrial CAD patterns and stores 2D pattern information.
2026-07-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S22 · Grade C
2D Pattern (DXF) Import/Export
DXF is a standard file format of industrial CAD patterns and stores 2D pattern information.
2026-07-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S22 · Grade C
2D Pattern (DXF) Import/Export
DXF is a standard file format of industrial CAD patterns and stores 2D pattern information.
2026-07-15. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗R03 · Grade C · inherited record
Inherited evidence R03
Company profile: more than 220,000 cotton producers supported in northern Cameroon; nine ginning plants; two oil mills.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R06 · Grade C · inherited record
Inherited evidence R06
About 95 percent of cotton fibre exported raw against 5 percent processed locally; industrialisation target of 50 percent local processing.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R07 · Grade C · inherited record
Inherited evidence R07
SND30 restates the 50 percent local-processing target by 2030.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R10 · Grade C · inherited record
Inherited evidence R10
Camtext SA: 12,000 t a year processed; about 12,000 jobs at the Dibamba hub and 3,000 at Garoua; return on investment near 11 years; optimal capacity around 2033.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R12 · Grade C · inherited record
Inherited evidence R12
CICAM capacity utilisation, July 2023 report: Garoua 33.7 percent, CICAM 1 48.9 percent, CICAM 2 10.83 percent; underutilisation cost about CFAF 2 billion in 2020.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R14 · Grade C · inherited record
Inherited evidence R14
Cameroon minimum wage (SMIG) XAF 41,875 a month in 2023, raised to XAF 43,969 a month from 23 February 2024, about US$76, a rise of 5 percent.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R15 · Grade C · inherited record
Inherited evidence R15
Average salary across sectors in Cameroon about US$359 a month.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R16 · Grade C · inherited record
Inherited evidence R16
Informal share of employment about 90 percent; standard 40-hour week, 48-hour maximum, overtime at 1.2 times.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R17 · Grade C · inherited record
Inherited evidence R17
Cambodia garment-sector minimum wage US$204 a month for 2024 (labour-cost benchmark).
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R28 · Grade C · inherited record
Inherited evidence R28
Fabric-defect-detection AI market US$523.4 million (2024) to US$6,522.1 million (2033) at 33.8 percent a year; Asia-Pacific about 46 percent in 2024.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R29 · Grade C · inherited record
Inherited evidence R29
Manual defect inspection 60 to 70 percent accurate, missing 20 to 30 percent of defects; computer vision above 90 percent across more than 40 defect types; line-scan inspection up to 60 metres a minute.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R30 · Grade C · inherited record
Inherited evidence R30
Generative AI in apparel 2023-2024 mainly design-side image generation (Midjourney, Stable Diffusion) across style, silhouette, colour and pattern.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R31 · Grade C · inherited record
Inherited evidence R31
By 2025-2026 the field moved to multi-model garment-design pipelines (fabric construction, shade, weave, silhouette) and physics-constrained generation coupling neural generation with simulation validation.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
Keep the definitions stable
45 terms, each with one definition for the whole paper. The punched row shows the chapters whose text uses the term.
Recurs inreading guide, not a citation
Cut to length
Chapters 01 to 02 fit in 60 minutes, with 8 minutes to spare.
Start chapter 01 · 2 chapters in 60 minWP10 · Draft web edition
From Mood Board to Specification
Cut length 2 chapters · 52 min
The PDF has passed its publication gates: 245 rendered A4 pages, 1.8 MB.
Download the verified PDFOn the same rack
WP01The Local-Processing GapWP02Measure Before You ModelWP03Seeing Every DefectRelated tools: Garment unit-economics and breakeven simulator, Water, energy and carbon per garment calculator, KPI cascade builder
Issued by Green Future Tech Limited, Hong Kong SAR. This research is not investment, legal or tax advice. Illustrative calculations require local validation before an operating or financing decision.