Research map / 3D vision / 3D generation
MV-Fashion: Towards Enabling Virtual Try-On and Size Estimation with Multi-View Paired Data
Hunor Laczkó, Libang Jia, Loc-Phat Truong, Diego Hernández, Sergio Escalera, Jordi Gonzalez, Meysam Madadi
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 |
|---|---|---|---|
| provide both frontal and rear garment catalogue images to IDM-VTON via shared IP-Adapter (ablation) | IDM-VTON · MV-Fashion multi-view VTON | FID: 12.907 -> 12.775 | Improved |
| provide both frontal and rear garment images (SSIM) (ablation) | IDM-VTON · MV-Fashion multi-view VTON | SSIM: 0.868 -> 0.873 | Improved |
| cross-view target poses (rear) with frontal-only garment image vs frontal single-view | IDM-VTON · MV-Fashion VTON | FID: 10.187 -> 12.907 | Hurt |
| augment prompt with draping-style text and train on MV-Fashion | IDM-VTON · MV-Fashion semantic controllability | qualitative style following | Mixed |
| train a multi-task size predictor jointly on all garment groups instead of per-group (ablation) | SPnet size predictor · MV-Fashion size estimation | MAE (cm): 4.904 -> 4.710 | Improved |
| multi-task training for jumpsuit group G5 instead of per-group (ablation) | SPnet size predictor · MV-Fashion size estimation (G5) | MAE (cm): 12.109 -> 4.295 | Improved |
| multi-task training for pants group G2 instead of per-group (ablation) | SPnet size predictor · MV-Fashion size estimation (G2) | MAE (cm): 3.006 -> 3.185 | Hurt |
| replace SegNet with SwinV2 and condition on target pose P^t (ablation) | Multi-task size predictor · MV-Fashion size estimation | MAE (cm): 4.710 -> 4.279 | Improved |
| increase splatfacto training views from 4 to 56 (ablation) | splatfacto · MV-Fashion NVS | PSNR: 24.633 -> 29.567 | Improved |
| increase splatfacto training views from 32 to 56 (ablation) | splatfacto · MV-Fashion NVS | PSNR: 29.211 -> 29.567 | Improved |
Closest papers by meaning
- MV-VTON: Multi-View Virtual Try-On with Diffusion Models (AAAI 2025 · similarity 0.92)
- 4D-DRESS: A 4D Dataset of Real-World Human Clothing With Semantic Annotations (CVPR 2024 · similarity 0.90)
- Robust-MVTON: Learning Cross-Pose Feature Alignment and Fusion for Robust Multi-View Virtual Try-On (CVPR 2025 · similarity 0.89)
- IMAGDressing-v1: Customizable Virtual Dressing (AAAI 2025 · similarity 0.89)
- VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction (CVPR 2025 · similarity 0.89)
- Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction (CVPR 2025 · 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.
