Research map / Image generation / Editing and style transfer
Toward Characteristic-Preserving Image-based Virtual Try-On Network
Bochao Wang, Huabin Zheng, Xiaodan Liang, Yimin Chen, Liang Lin, Meng Yang
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 the composition mask (merge warped clothes with UNet rendered person) instead of UNet-only rendering (ablation) | CP-VTON Try-On Module · LARGE clothes, user study | preference over variant (%): 72.5% | Improved |
| add the composition mask instead of UNet-only rendering (ablation) | CP-VTON Try-On Module · SMALL clothes, user study | preference over variant (%): 42% | No clear effect |
| add L1 regularization on the composition mask (ablation) | CP-VTON Try-On Module · LARGE clothes, user study | preference over variant (%): 84.5% | Improved |
| add L1 regularization on the composition mask (ablation) | CP-VTON Try-On Module · SMALL clothes, user study | preference over variant (%): 38.5% | No clear effect |
| replace VITON with CP-VTON pipeline using identical person representation | virtual try-on · LARGE clothes, user study | preference over VITON (%): 67.5% | Improved |
| replace VITON with CP-VTON pipeline | virtual try-on · SMALL clothes, user study | preference over VITON (%): 55.0% | Improved |
| replace shape context matching (SCMM) with learned GMM | clothes warping · LARGE and SMALL, warped-paste user study | rated more realistic (%): 49.5% and 42.0% | No clear effect |
| replace SCMM with GMM | clothes warping · matching time per pair | time (s): 2.01s (SCMM CPU) -> 0.52s (GMM CPU), 0.06s GPU | Improved |
Closest papers by meaning
- Toward Realistic Virtual Try-on Through Landmark Guided Shape Matching (AAAI 2021 · similarity 0.95)
- Full-Range Virtual Try-On With Recurrent Tri-Level Transform (CVPR 2022 · similarity 0.93)
- Image Based Virtual Try-On Network From Unpaired Data (CVPR 2020 · similarity 0.92)
- Virtual Try-On: Real-Time Interactive Hybrid Network with High-Fidelity (AAAI 2024 · similarity 0.92)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · similarity 0.91)
- Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On (ICLR 2025 · similarity 0.91)
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.
