Research map / Image generation / Editing and style transfer
FW-GAN: Flow-Navigated Warping GAN for Video Virtual Try-On
Haoye Dong, Xiaodan Liang, Xiaohui Shen, Bowen Wu, Bing-Cheng Chen, Jian Yin
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 |
|---|---|---|---|
| add parsing constraint loss (ablation) | FW-GAN · VVT video virtual try-on | FID (I3D): 7.30 -> 7.052 | Improved |
| add parsing constraint loss (ablation) | FW-GAN · VVT video virtual try-on | FID (ResNeXt-101): 19.34 -> 23.94 | Hurt |
| add flow-embedding discriminator (ablation) | FW-GAN · VVT video virtual try-on | FID (I3D): 7.45 -> 7.052 | Improved |
| add flow-embedding discriminator (ablation) | FW-GAN · VVT video virtual try-on | FID (ResNeXt-101): 20.78 -> 23.94 | Hurt |
| add optical flow module (ablation) | FW-GAN · VVT video virtual try-on | FID (I3D): 6.98 -> 7.052 | Hurt |
| add optical flow module (ablation) | FW-GAN · VVT video virtual try-on | FID (ResNeXt-101): 13.17 -> 23.94 | Hurt |
| add warping net (grid) (ablation) | FW-GAN · VVT video virtual try-on | FID (I3D): 7.04 -> 7.052 | No clear effect |
| add warping net (grid) (ablation) | FW-GAN · VVT video virtual try-on | FID (ResNeXt-101): 15.31 -> 23.94 | Hurt |
| add warping net, flow and parsing loss together (ablation) | FW-GAN · VVT video virtual try-on | FID (I3D): 6.57 -> 7.052 | Hurt |
| add warping net, flow and parsing loss together (ablation) | FW-GAN · VVT video virtual try-on | FID (ResNeXt-101): 14.01 -> 23.94 | Hurt |
| use FW-GAN instead of VITON/CP-VTON | FW-GAN · VVT video virtual try-on | FID (I3D): 30.05 -> 7.052 | Improved |
| use FW-GAN instead of VITON/CP-VTON | FW-GAN · VVT video virtual try-on | FID (ResNeXt-101): 129.74 -> 23.94 | 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.
- VITON — VITON: An Image-Based Virtual Try-On Network (CVPR 2018) · better on 4 of 4 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
- Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GAN (NeurIPS 2021 · similarity 0.92)
- Towards Multi-Pose Guided Virtual Try-On Network (ICCV 2019 · similarity 0.91)
- SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.88)
- CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model (CVPR 2024 · similarity 0.88)
- CycleVTON: A Cycle Mapping Framework for Parser-Free Virtual Try-On (AAAI 2024 · similarity 0.87)
- MV-VTON: Multi-View Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.87)
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.
