Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.16502 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917279546998784 |
|---|---|
| author | Tao, Zeng Jiang, Ying Chen, Yunuo Xie, Tianyi Wang, Huamin Wu, Yingnian Yang, Yin Kumar, Abishek Sampath Tashiro, Kenji Jiang, Chenfanfu |
| author_facet | Tao, Zeng Jiang, Ying Chen, Yunuo Xie, Tianyi Wang, Huamin Wu, Yingnian Yang, Yin Kumar, Abishek Sampath Tashiro, Kenji Jiang, Chenfanfu |
| contents | Recent advances in garment pattern generation have shown promising progress. However, existing feed-forward methods struggle with diverse poses and viewpoints, while optimization-based approaches are computationally expensive and difficult to scale. This paper focuses on sewing pattern generation for garment modeling and fabrication applications that demand editable, separable, and simulation-ready garments. We propose DressWild, a novel feed-forward pipeline that reconstructs physics-consistent 2D sewing patterns and the corresponding 3D garments from a single in-the-wild image. Given an input image, our method leverages vision-language models (VLMs) to normalize pose variations at the image level, then extract pose-aware, 3D-informed garment features. These features are fused through a transformer-based encoder and subsequently used to predict sewing pattern parameters, which can be directly applied to physical simulation, texture synthesis, and multi-layer virtual try-on. Extensive experiments demonstrate that our approach robustly recovers diverse sewing patterns and the corresponding 3D garments from in-the-wild images without requiring multi-view inputs or iterative optimization, offering an efficient and scalable solution for realistic garment simulation and animation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16502 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images Tao, Zeng Jiang, Ying Chen, Yunuo Xie, Tianyi Wang, Huamin Wu, Yingnian Yang, Yin Kumar, Abishek Sampath Tashiro, Kenji Jiang, Chenfanfu Computer Vision and Pattern Recognition Recent advances in garment pattern generation have shown promising progress. However, existing feed-forward methods struggle with diverse poses and viewpoints, while optimization-based approaches are computationally expensive and difficult to scale. This paper focuses on sewing pattern generation for garment modeling and fabrication applications that demand editable, separable, and simulation-ready garments. We propose DressWild, a novel feed-forward pipeline that reconstructs physics-consistent 2D sewing patterns and the corresponding 3D garments from a single in-the-wild image. Given an input image, our method leverages vision-language models (VLMs) to normalize pose variations at the image level, then extract pose-aware, 3D-informed garment features. These features are fused through a transformer-based encoder and subsequently used to predict sewing pattern parameters, which can be directly applied to physical simulation, texture synthesis, and multi-layer virtual try-on. Extensive experiments demonstrate that our approach robustly recovers diverse sewing patterns and the corresponding 3D garments from in-the-wild images without requiring multi-view inputs or iterative optimization, offering an efficient and scalable solution for realistic garment simulation and animation. |
| title | DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.16502 |