AI Paper Atlas

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

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
replace T5 text encoder with MGSA (MLLM + learnable queries + alignment loss) (ablation)UniFit Stage I · VITON-HD single-garment try-onFID: 9.133 -> 8.813Improved
add semantic alignment loss Lalign (ablation)UniFit Stage I · VITON-HD single-garment try-onKID: 0.951 -> 0.785Improved
add spatial attention focusing loss Lfocus (ablation)UniFit Stage I · VITON-HD single-garment try-onKID: 0.835 -> 0.785Improved
UniFit vs best prior on garment reconstructionUniFit · VITON-HD garment reconstructionFID: 13.57 -> 12.58Improved
UniFit vs MV-VTON on multi-view try-onUniFit · MVG multi-view try-onFID/LPIPS/KID: FID 37.09 -> 35.62; LPIPS 0.062 -> 0.072Mixed
UniFit vs baselines on single-garment try-onUniFit · VITON-HD single-garment try-onSSIM: 0.895 (FitDiT) vs 0.883Mixed

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy