Research map / Video / Video generation
TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On
Dingbao Shao, Song Wu, Shenyi Wang, Ye Wang, Ziheng Tang, Fei Liu, Jiang Lin, Xinyu Chen, Qian Wang, Ying Tai, Jian Yang, Zili Yi
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 TripVVT-10K to training (ablation) | TripVVT · TripVVT-Bench ablation | VFID-R: 0.4569 -> 0.3163 | Improved |
| add TripVVT-10K to training (ablation) | TripVVT · TripVVT-Bench ablation | SSIM: 0.7605 -> 0.8538 | Improved |
| add human-mask conditioning (ablation) | TripVVT · TripVVT-Bench ablation | VFID-R: 5.9749 -> 0.3163 | Improved |
| use human mask instead of garment mask (ablation) | TripVVT · TripVVT-Bench ablation | VFID-I: 28.5826 -> 20.7245 | Improved |
| add pose guidance (ablation) | TripVVT · TripVVT-Bench ablation | VFID-I: 33.6635 -> 20.7245 | Improved |
| add pose guidance (ablation) | TripVVT · TripVVT-Bench ablation | CLIP-I: 0.6989 -> 0.7110 | Mixed |
| train on TripVVT-10K vs mask-based baselines on ViViD-S | TripVVT · ViViD-S test | VFID-R: 0.5073 -> 0.3315 | Improved |
| coarse human mask instead of garment mask on ViViD-S background | TripVVT · ViViD-S test | BG-L1: 0.0493 -> 0.0624 | Hurt |
| TripVVT vs MagicTryOn on TripVVT-Bench SSIM | TripVVT · TripVVT-Bench | SSIM: 0.8641 -> 0.8538 | Hurt |
| TripVVT vs MagicTryOn on TripVVT-Bench background error | TripVVT · TripVVT-Bench | BG-L1: 0.0515 -> 0.0852 | Hurt |
| TripVVT vs Kling on try-on success | TripVVT · TripVVT-Bench | Gemini-SR: 78% -> 91% | Improved |
Later papers that compared with this method
1 later accepted paper reports TripVVT as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors (NeurIPS 2026 · 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
- InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors (NeurIPS 2026 · similarity 0.90)
- Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction (CVPR 2025 · similarity 0.90)
- SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.89)
- BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training (CVPR 2025 · similarity 0.89)
- OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation (NeurIPS 2026 · similarity 0.88)
- FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization (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.
