Research map / Video / Video generation
iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance
Jun Zheng, Zhengze Xu, Mengting Chen, Jing Wang, Jinsong Lan, Xiaoyong Zhu, Kaifu Zhang, Bo Zheng, Xiaodan Liang
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 VVT-Interact training data only to baseline (ablation) | Wan2.1-VACE VVT baseline · VVT-Interact (paired) | ISR: 0.4766 -> 0.4779 | No clear effect |
| add garment-agnostic 3D hand spatial guidance (ablation) | baseline + data · VVT-Interact (paired) | ISR: 0.4779 -> 0.5174 | Improved |
| add action captions with A-RoPE semantic guidance (ablation) | baseline + data + spatial guidance · VVT-Interact (paired) | ISR: 0.5174 -> 0.5987 | Improved |
| add action-aware constraint loss (ablation) | full iTryOn without AC loss · VVT-Interact (paired) | ISR: 0.5987 -> 0.6100 | Improved |
| add action-aware constraint loss (ablation) | full iTryOn without AC loss · VVT-Interact (paired) | FVD: 379.7348 -> 380.5578 | Hurt |
| add action-aware constraint loss (ablation) | full iTryOn without AC loss · VVT-Interact (paired) | VFID_R: 0.6652 -> 0.6033 | Improved |
| add VVT-Interact data only (ablation) | baseline · VVT-Interact (paired) | FVD: 419.0978 -> 394.1350 | Improved |
| use iTryOn instead of prior VVT methods | video virtual try-on · VVT-Interact (paired) | ISR: 0.4838 (CatV2TON) -> 0.6100 | Improved |
Closest papers by meaning
- Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction (CVPR 2025 · similarity 0.90)
- InstructVVT: Instruction-Driven Video Virtual Try-On without Auxiliary Spatial Priors (NeurIPS 2026 · similarity 0.90)
- SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.89)
- Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On (ICLR 2025 · similarity 0.89)
- OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation (NeurIPS 2026 · similarity 0.88)
- CycleVTON: A Cycle Mapping Framework for Parser-Free Virtual Try-On (AAAI 2024 · 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.
