Research map / Video / Video segmentation and tracking
ClothFormer: Taming Video Virtual Try-On in All Module
Jianbin Jiang, Tan Wang, He Yan, Junhui Liu
Check 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 |
|---|---|---|---|
| Use ClothFormer instead of PBAFN | Video virtual try-on · VVT | SSIM: 0.870 -> 0.921 | Improved |
| Use ClothFormer instead of PBAFN | Video virtual try-on · VVT | LPIPS: 0.157 -> 0.081 | Improved |
| Use ClothFormer instead of PBAFN | Video virtual try-on · VVT | VFID I3D: 4.516 -> 3.967 | Improved |
| Use ClothFormer instead of PBAFN* | Video virtual try-on · Our dataset | VFID I3D: 6.132 -> 5.024 | Improved |
| Add the Anti-occlusion Warp Module (ablation) | ClothFormer · Our dataset | SSIM: 0.953 -> 0.958 | Improved |
| Add the Anti-occlusion Warp Module (ablation) | ClothFormer · Our dataset | LPIPS: 0.047 -> 0.042 | Improved |
| Add the Appearance-flow Tracking Module (ablation) | ClothFormer · Our dataset | VFID I3D: 5.140 -> 5.024 | Improved |
| Replace U-Net with the MPDT generator (ablation) | ClothFormer try-on module · Our dataset | VFID I3D: 5.653 -> 5.024 | Improved |
| Reduce MPDT channels from 256 to 96 and blocks from 8 to 6 (ablation) | ClothFormer · Our dataset | VFID I3D: 5.024 -> 5.208 | Hurt |
Later papers that compared with this method
2 later accepted papers report ClothFormer as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion Models (AAAI 2025 · better on 0 of 1 shared result)
- WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models (ECCV 2024 · better on 0 of 1 shared result)
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
- High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions (ECCV 2022 · similarity 0.91)
- Style-Based Global Appearance Flow for Virtual Try-On (CVPR 2022 · similarity 0.90)
- WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models (ECCV 2024 · similarity 0.90)
- Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction (CVPR 2025 · similarity 0.89)
- SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.89)
- InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors (NeurIPS 2026 · similarity 0.88)
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.
