Research map / Video / Video generation
WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models
Zijian He, Peixin Chen, Guangrun Wang, Guanbin Li, Philip Torr, Liang Lin
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 fully cross-frame attention to image-based model (ablation) | WildVidFit · TikTok | VFID: 13.45 -> 12.14 | Improved |
| add VideoMAE guidance (L_MAE) (ablation) | WildVidFit · TikTok | VFID: 12.14 -> 10.64 | Improved |
| add DINO-V2 feature similarity guidance (L_SIM) (ablation) | WildVidFit · TikTok | VFID: 10.64 -> 10.28 | Improved |
| add temporal co-denoising over overlapping clips (ablation) | WildVidFit · TikTok | VFID: 10.28 -> 9.87 | Improved |
| add garment edge map to garment representation (ablation) | WildVidFit image try-on · VITON-HD | FID: 8.93 -> 8.67 | Improved |
| raise classifier-free guidance scale from 1 to 2 (ablation) | WildVidFit image try-on · VITON-HD | FID: 9.47 -> 8.67 | Improved |
| raise classifier-free guidance scale from 2 to 3 (ablation) | WildVidFit image try-on · VITON-HD | FID: 8.67 -> 8.68 | No clear effect |
| video-trained ClothFormer versus image-trained WildVidFit with diffusion guidance | video try-on · VVT | VFID: 4.192 vs 4.202 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- ClothFormer — ClothFormer: Taming Video Virtual Try-On in All Module (CVPR 2022) · 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
- SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.92)
- Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction (CVPR 2025 · similarity 0.92)
- InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors (NeurIPS 2026 · similarity 0.91)
- Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On (CVPR 2024 · similarity 0.90)
- BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training (CVPR 2025 · similarity 0.90)
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.89)
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.
