Research map / Vision-language and multimodal / Cross-modal learning
UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment
Wei Zhang, Yeying Jin, Xin Li, Yan Zhang, Xiaofeng Cong, Cong Wang, Fengcai Qiao, Zhichao Lian
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 |
|---|---|---|---|
| replace T5 text encoder with MGSA (MLLM + learnable queries + alignment loss) (ablation) | UniFit Stage I · VITON-HD single-garment try-on | FID: 9.133 -> 8.813 | Improved |
| add semantic alignment loss Lalign (ablation) | UniFit Stage I · VITON-HD single-garment try-on | KID: 0.951 -> 0.785 | Improved |
| add spatial attention focusing loss Lfocus (ablation) | UniFit Stage I · VITON-HD single-garment try-on | KID: 0.835 -> 0.785 | Improved |
| UniFit vs best prior on garment reconstruction | UniFit · VITON-HD garment reconstruction | FID: 13.57 -> 12.58 | Improved |
| UniFit vs MV-VTON on multi-view try-on | UniFit · MVG multi-view try-on | FID/LPIPS/KID: FID 37.09 -> 35.62; LPIPS 0.062 -> 0.072 | Mixed |
| UniFit vs baselines on single-garment try-on | UniFit · VITON-HD single-garment try-on | SSIM: 0.895 (FitDiT) vs 0.883 | Mixed |
Closest papers by meaning
- OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation (NeurIPS 2026 · similarity 0.88)
- IMAGDressing-v1: Customizable Virtual Dressing (AAAI 2025 · similarity 0.88)
- M&M VTO: Multi-Garment Virtual Try-On and Editing (CVPR 2024 · similarity 0.88)
- Correpondence Alignment For Improved Virtual Try-On (NeurIPS 2026 · similarity 0.88)
- Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On (ICLR 2025 · similarity 0.88)
- MV-VTON: Multi-View Virtual Try-On with Diffusion Models (AAAI 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.
