Research map / Image generation / Editing and style transfer
FDM-MFVT: Few-step Sampling Diffusion Model for Mask-Free Virtual Try-On
Jiaxin Liu, XIAOYE LIANG, Lai Jiang, Jun Liu, Mai Xu
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 OANO noise optimization (ablation) | FDM-MFVT · MFVT ablation | LPIPS: 0.121 -> 0.091 | Improved |
| add OANO noise optimization (ablation) | FDM-MFVT · MFVT ablation | SSIM: 0.864 -> 0.879 | Improved |
| add OANO noise optimization (ablation) | FDM-MFVT · MFVT ablation | FID: 8.417 -> 8.363 | Improved |
| add OANO noise optimization (ablation) | FDM-MFVT · MFVT ablation | KID: 1.019 -> 0.865 | Improved |
| add IDT module (ablation) | FDM-MFVT · MFVT ablation | LPIPS: 0.135 -> 0.091 | Improved |
| add IDT module (ablation) | FDM-MFVT · MFVT ablation | SSIM: 0.859 -> 0.879 | Improved |
| add IDT module (ablation) | FDM-MFVT · MFVT ablation | FID: 8.378 -> 8.363 | Improved |
| add IDT module (ablation) | FDM-MFVT · MFVT ablation | KID: 1.142 -> 0.865 | Improved |
| use FDM-MFVT instead of Any2AnyTryon at 6 steps | mask-free try-on · MFVT Dresses | FID: 10.461 -> 8.431 | Improved |
| use FDM-MFVT instead of Any2AnyTryon at 6 steps | mask-free try-on · MFVT Dresses | SSIM: 0.771 -> 0.872 | Improved |
| use FDM-MFVT at 6 steps vs ITA-MDT mask-based | mask-based try-on · DressCode Upper unpaired | FID: 20.437 -> 11.231 | Improved |
| use FDM-MFVT at 6 steps vs ITA-MDT mask-based | mask-based try-on · VTON-HD unpaired | FID: 11.054 -> 8.687 | Improved |
Closest papers by meaning
- Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On (CVPR 2024 · similarity 0.90)
- BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training (CVPR 2025 · similarity 0.90)
- ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On (CVPR 2025 · similarity 0.90)
- Cascaded Diffusion Models for Virtual Try-On: Improving Control and Resolution (AAAI 2025 · similarity 0.89)
- OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-On (AAAI 2025 · similarity 0.89)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 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.
