Research map / Image generation / Text-to-image diffusion
FabricGen: Microstructure-Aware Woven Fabric Generation
Yingjie Tang, Di Luo, Zixiong Wang, Xiaoli Ling, Jian Yang, Beibei Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fine-tune Qwen2.5-14B into WeavingLLM for weaving drafts (ablation) | weaving draft generation · herringbone twill draft | Fourier cosine similarity: 0.583 -> 0.701 | Improved |
| fine-tune Qwen2.5-14B into WeavingLLM for weaving drafts (ablation) | weaving draft generation · spot bronson lace draft | LPIPS: 0.385 -> 0.152 | Improved |
| use fine-tuned WeavingLLM instead of GPT-5 (ablation) | weaving draft generation · herringbone twill and spot bronson lace | LPIPS: 0.245 -> 0.125; 0.19 -> 0.152 | Improved |
| add prompt-tuning with fabric expertise to WeavingLLM (ablation) | WeavingLLM parameter prediction · herringbone twill and satin renderings | qualitative appearance | Improved |
| fine-tune FLUX on microstructure-free fabric albedos (ablation) | macro-texture generator · fabric albedo generation | qualitative artifacts | Improved |
| add yarn sliding and flyaway fibers (ablation) | procedural model · comparison to captured photo | LPIPS: 0.499 -> 0.352 | Improved |
| use FabricGen instead of DressCode/MatFuse | text-to-fabric generation · text conditioning | CLIP Score: 0.307 -> 0.317 (DressCode), 0.240 -> 0.317 (MatFuse) | Improved |
| use FabricGen instead of MatFuse with image conditioning | image-conditioned generation · text and image conditioning | CLIP-I Score: 0.722 -> 0.827 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MatFuse — MatFuse: Controllable Material Generation with Diffusion Models (CVPR 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- TexTile: A Differentiable Metric for Texture Tileability (CVPR 2024 · similarity 0.87)
- Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis (CVPR 2025 · similarity 0.86)
- MatFuse: Controllable Material Generation with Diffusion Models (CVPR 2024 · similarity 0.86)
- Single Mesh Diffusion Models with Field Latents for Texture Generation (CVPR 2024 · similarity 0.84)
- VLMaterial: Procedural Material Generation with Large Vision-Language Models (ICLR 2025 · similarity 0.84)
- MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation (CVPR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
