AI Paper Atlas

Research map / Image generation / Image restoration

Rethinking Expressivity and Degradation-Awareness in Attention for All-in-One Blind Image Restoration

Bin Ren, Runyi Yang, Qi Ma, Xu Zheng, Mengyuan Liu, Danda Pani Paudel, Luc Van Gool, Rita Cucchiara, Nicu Sebe

ICLR 2026 · Image generation › Image restoration · approach: Efficient restoration architectures

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 nonlinear value transform (ablation)prompt-free PromptIR · 3-degradation averagePSNR: 30.75 -> 32.54Improved
add global spatial token (GST) (ablation)prompt-free PromptIR · 3-degradation averagePSNR: 30.75 -> 32.67Improved
combine nonlinear value and GST (ablation)prompt-free PromptIR · 3-degradation averagePSNR: 30.75 -> 32.96Improved
use residual form of nonlinear value instead of in-place (GELU) (ablation)ExDA-Tiny · 3-degradation averagePSNR: 32.45 -> 32.71Improved
use residual form instead of in-place (Sigmoid) (ablation)ExDA-Tiny · 3-degradation averagePSNR: 32.30 -> 32.63Improved
use learnable parametric mapping instead of non-parametric GELU (ablation)ExDA-Tiny · 3-degradation averagePSNR: 32.30 -> 32.71Improved
apply nonlinear values in both encoder and decoder instead of encoder-only (ablation)ExDA-Tiny · 3-degradation averagePSNR: 32.65 -> 32.71Improved
apply nonlinear values in both encoder and decoder instead of decoder-only (ablation)ExDA-Tiny · 3-degradation averagePSNR: 32.60 -> 32.71Improved
use GST stride 2 instead of 1 (ablation)ExDA-Tiny · 3-degradation averagePSNR: 32.45 -> 32.71Improved
use GST stride 2 instead of 4 or 8 (ablation)ExDA-Tiny · 3-degradation averagePSNR: 32.52 and 32.40 -> 32.71Improved
add GST to improve degradation separability (ablation)ExDA · embedding clusteringNMI / ARI: NMI 0.71 -> 0.88; ARI 0.56 -> 0.89Improved
use nonlinear value instead of linear value in synthetic restoration (ablation)attention · MNIST restorationPSNR: 19.2 -> 25.1 dBImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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