Research map / 3D vision / Human pose estimation
M3D-VTON: A Monocular-to-3D Virtual Try-On Network
Fuwei Zhao, Zhenyu Xie, Michael Kampffmeyer, Haoye Dong, Songfang Han, Tianxiang Zheng, Tao Zhang, 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 self-adaptive pre-alignment before TPS warping (ablation) | Clothing warping branch · MPV-3D | IoU: 0.708 -> 0.737 | Improved |
| add segmentation guidance to TFM (ablation) | TFM · MPV-3D full-body | FID: 16.52 -> 16.01 | Improved |
| add segmentation guidance to TFM (ablation) | TFM · MPV-3D full-body | SSIM: 0.9348 -> 0.9434 | Improved |
| add depth guidance to TFM (ablation) | TFM · MPV-3D full-body | FID: 16.52 -> 15.96 | Improved |
| add depth guidance to segmentation-guided TFM (ablation) | TFM · MPV-3D full-body | FID: 16.01 -> 15.74 | Improved |
| add depth guidance to segmentation-guided TFM (ablation) | TFM · MPV-3D full-body | SSIM: 0.9434 -> 0.9435 | No clear effect |
| add gradient image input to DRM (ablation) | DRM · MPV-3D front depth | RMSE: 5.8369 -> 5.7650 | Improved |
| add gradient image input to DRM (ablation) | DRM · MPV-3D front depth | Sq. error: 0.0824 -> 0.0896 | Hurt |
| add depth gradient loss to DRM with gradient input (ablation) | DRM · MPV-3D front depth | Sq. error: 0.0896 -> 0.0801 | Improved |
| add depth gradient loss to DRM with gradient input (ablation) | DRM · MPV-3D front depth | RMSE: 5.7650 -> 5.7420 | Improved |
| compare M3D-VTON to PIFu on 3D try-on depth | M3D-VTON · MPV-3D | RMSE: 27.57 -> 11.27 | Improved |
| compare M3D-VTON to NormalGAN on 3D try-on human evaluation | M3D-VTON · MPV-3D | human evaluation: 21.3% -> 67.4% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Deephuman — DeepHuman: 3D Human Reconstruction From a Single Image (ICCV 2019) · better on 3 of 3 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
- VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction (CVPR 2025 · similarity 0.92)
- IPVTON: Image-based 3D Virtual Try-on with Image Prompt Adapter (AAAI 2025 · similarity 0.91)
- MV-VTON: Multi-View Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.91)
- Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On (ICLR 2025 · similarity 0.90)
- Robust-MVTON: Learning Cross-Pose Feature Alignment and Fusion for Robust Multi-View Virtual Try-On (CVPR 2025 · similarity 0.89)
- Correpondence Alignment For Improved Virtual Try-On (NeurIPS 2026 · 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.
