AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

DR.Experts: Differential Refinement of Distortion-Aware Experts for Blind Image Quality Assessment

Bohan Fu, Guanyi Qin, Fazhan Zhang, Zihao Huang, Mingxuan Li, Runze Hu

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment · 0 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
add DSDM to image encoder (ablation)Image Encoder · KonIQSRCC: 0.916 -> 0.930Improved
add DSDM to image encoder (ablation)Image Encoder · LIVECSRCC: 0.857 -> 0.885Improved
add DDWM on top of DSDM (ablation)DSDM · KonIQSRCC: 0.930 -> 0.941Improved
add DDWM on top of DSDM (ablation)DSDM · LIVECSRCC: 0.885 -> 0.914Improved
use raw DA-CLIP features alone instead of image encoder (ablation)Image Encoder · KonIQSRCC: 0.916 -> 0.720Hurt
add bridging features to Dis and Sem groups (ablation)DDWM feature group · LIVECSRCC: 0.909 -> 0.914Improved
add distortion features to Sem and Bri groups (ablation)DDWM feature group · LIVECSRCC: 0.913 -> 0.914Improved
add semantic features to Dis and Bri groups (ablation)DDWM feature group · LIVECPLCC: 0.919 -> 0.926Improved
combine all three feature groups instead of only distortion features (ablation)DDWM feature group · KonIQSRCC: 0.933 -> 0.941Improved
use DR.Experts instead of LODA when trained on KonIQ and tested on LIVECDR.Experts · Cross-datasetSRCC: 0.811 -> 0.841Improved
use DR.Experts instead of LODA when trained on LIVEFB and tested on LIVECDR.Experts · Cross-datasetSRCC: 0.805 -> 0.807No clear effect
train with only 60%/40%/20% of data (DR.Experts vs LoDa at 20%)DR.Experts · LIVEC (20% data)SRCC: 0.815 -> 0.837Improved

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