Research map / Video / Video segmentation and tracking
Dressing in the Wild by Watching Dance Videos
Xin Dong, Fuwei Zhao, Zhenyu Xie, Xijin Zhang, Daniel K. Du, Min Zheng, Xiang Long, Xiaodan Liang, Jianchao Yang
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 |
|---|---|---|---|
| Combine 2D pixel flow with 3D vertex flow (ablation) | wFlow garment transfer · Dance50k | FID: 12.077 -> 8.809 | Improved |
| Combine 2D pixel flow with 3D vertex flow (ablation) | wFlow garment transfer · DeepFashion | FID: 63. 136 -> 57.652 | Improved |
| Add pixel flow to vertex flow (ablation) | wFlow pose transfer · Dance50k | SSIM: 0.922 -> 0.920 | Hurt |
| Add pixel flow to vertex flow (ablation) | wFlow pose transfer · DeepFashion | SSIM: 0.847 -> 0.844 | Hurt |
| Add cycle optimization (ablation) | wFlow garment transfer · Dance50k | FID: 12.106 -> 8.809 | Improved |
| Add cycle optimization (ablation) | wFlow garment transfer · DeepFashion | FID: 71.016 -> 57.652 | Improved |
| Use pixel flow alone instead of combined flow (ablation) | wFlow garment transfer · Dance50k | FID: 8.809 -> 12.077 | Hurt |
| Use vertex flow alone instead of combined flow (ablation) | wFlow garment transfer · Dance50k | FID: 8.809 -> 9.455 | Hurt |
| Use wFlow instead of LWG | garment transfer · Dance50k | FID: 13.080 -> 8.809 | Improved |
| Use wFlow instead of LWG | garment transfer · DeepFashion | LPIPS: 0.225 -> 0.187 | Improved |
Closest papers by meaning
- WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models (ECCV 2024 · similarity 0.90)
- DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images (NeurIPS 2026 · similarity 0.88)
- High-Fidelity Neural Human Motion Transfer From Monocular Video (CVPR 2021 · similarity 0.88)
- FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization (NeurIPS 2026 · similarity 0.87)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.87)
- IMAGDressing-v1: Customizable Virtual Dressing (AAAI 2025 · similarity 0.86)
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.
