AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Reference-Free Quality Assessment for Virtual Try-On via Human Feedback

Yuki Hirakawa, Takashi Wada, Ryotaro Shimizu, Takuya Furusawa, Yuki Saito, Ryosuke Araki, Tianwei Chen, Fan Mo, Yoshimitsu Aoki

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment

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
add Interleaved Cross-Attention (ICA) (ablation)VTON-IQA · VTON-QBench testSRCC: 0.617 -> 0.750Improved
add Interleaved Cross-Attention (ICA) (ablation)VTON-IQA · VTON-QBench testA_micro: 0.747 -> 0.790Improved
add Interleaved Cross-Attention (ICA) (ablation)VTON-IQA · VTON-QBench testR2: 0.372 -> 0.553Improved
add Interleaved Cross-Attention (ICA) (ablation)VTON-IQA · VTON-QBench testPLCC: 0.615 -> 0.751Improved
fine-tune on VTON-QBench instead of zero-shot DINOv3DINOv3 scorer · VTON-QBench testSRCC: 0.244 -> 0.617Improved
fine-tune only last half of layers instead of full network (ablation)VTON-IQA · VTON-QBench test (backbone and fine-tuning ablation)SRCC: 0.226 -> 0.750Improved
fine-tune last half instead of last quarter of layers (ablation)VTON-IQA · VTON-QBench test (backbone and fine-tuning ablation)SRCC: 0.746 -> 0.750No clear effect
scale backbone from ViT-B/16 to ViT-L/16 (ablation)VTON-IQA · VTON-QBench test (backbone and fine-tuning ablation)SRCC: 0.726 -> 0.750Improved
add synthetic pairs to real training data (ablation)VTON-IQA · VTON-QBench test S (train data ablation)SRCC: 0.642 -> 0.732Improved
add synthetic pairs to real training data (ablation)VTON-IQA · VTON-QBench test R (train data ablation)SRCC: 0.739 -> 0.738No clear effect
evaluate on unknown VTON models instead of knownVTON-IQA · VTON-QBench cross-group generalizationSRCC: 0.733 -> 0.676Hurt
evaluate VTON-IQA against human annotator agreementVTON-IQA · VTON-QBench test (half-annotator labels, 10 runs)A_micro: 0.791 -> 0.783No clear effect

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