Research map / Image generation / Text-to-image diffusion
WearWow: Native 2K Multi-Garment Virtual Try-On via Adaptive Token Packing and Preference Alignment
Xujie Zhang, Runyan Du, Song Chang, Jiang Li, Dongliang Shao, Liping Wu, Luo Wei, Xiaochao Qu, Luoqi Liu, 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 Adaptive 2D Token Packing instead of cascaded SR (ablation) | WearWow · Ablation study | LPIPS: 0.1237 -> 0.0870 | Improved |
| add Adaptive 2D Token Packing instead of cascaded SR (ablation) | WearWow · Ablation study | SSIM: 0.8502 -> 0.8677 | Improved |
| add Adaptive 2D Token Packing (vs downscaled references) (ablation) | WearWow · Ablation study | LPIPS: 0.0923 -> 0.0870 | Improved |
| add Adaptive 2D Token Packing (vs downscaled references) (ablation) | WearWow · Ablation study | SSIM: 0.8468 -> 0.8677 | Improved |
| add Adaptive 2D Token Packing (vs downscaled references) (ablation) | WearWow · Ablation study | CLIP score: 0.2654 -> 0.2690 | Improved |
| add Cloth Distribution Reward to Semantic Guidance Reward (ablation) | WearWow MTR · Ablation study | LPIPS: 0.0874 -> 0.0870 | Improved |
| add Cloth Distribution Reward to Semantic Guidance Reward (ablation) | WearWow MTR · Ablation study | SSIM: 0.8599 -> 0.8677 | Improved |
| add Semantic Guidance Reward to Cloth Distribution Reward (ablation) | WearWow MTR · Ablation study | LPIPS: 0.0961 -> 0.0870 | Improved |
| add Semantic Guidance Reward to Cloth Distribution Reward (ablation) | WearWow MTR · Ablation study | SSIM: 0.8596 -> 0.8677 | Improved |
| add Semantic Guidance Reward to Cloth Distribution Reward (ablation) | WearWow MTR · Ablation study | CLIP score: 0.2664 -> 0.2690 | Improved |
| WearWow vs best commercial baseline Nano Banana Pro | WearWow · WearWow-2K (native 2K multi-garment) | FID: 8.1823 -> 7.5400 | Improved |
| WearWow vs CatVTON on single-garment | WearWow · VITON-HD + DressCode (1024x768) | SSIM: 0.8950 -> 0.8815 | Hurt |
Closest papers by meaning
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models (CVPR 2025 · similarity 0.88)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · similarity 0.87)
- Towards Squeezing-Averse Virtual Try-On via Sequential Deformation (AAAI 2024 · similarity 0.87)
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.87)
- AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario (NeurIPS 2024 · similarity 0.87)
- Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On (ICLR 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.
