AI Paper Atlas

Research map / Image generation / Image restoration

Dual-level Prototype Learning for Composite Degraded Image Restoration

Zhongze Wang, Haitao Zhao, Lujian Yao, Jingchao Peng, Kaijie Zhao

ICCV 2025 · Image generation › Image restoration · approach: Efficient restoration architectures · 1 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 degradation-level prototypes Pdeg to baseline (ablation)Baseline U-Net · VCDPSNR (dB): 20.59 -> 21.10Improved
add factor-level prototypes Pfac on top of Pdeg (ablation)DPL · VCDPSNR (dB): 21.10 -> 22.71Improved
add DSETB scene cross attention (ablation)DPL · VCDPSNR (dB): 22.71 -> 23.08Improved
add prototype scatter loss Lpsl (ablation)DPL · VCDPSNR (dB): 23.08 -> 25.27Improved
add within-degradation-farthest scatter constraint to loss (vs Lvar1) (ablation)Lpsl · VCDPSNR (dB): 19.68 -> 25.27Improved
use inverse ratio-trace form (vs Lvar2 without inverse) (ablation)Lpsl · VCDPSNR (dB): 21.19 -> 25.27Improved
use ratio-trace form instead of difference form (Lvar3) (ablation)Lpsl · VCDPSNR (dB): 23.62 -> 25.27Improved
use Lpsl instead of contrastive loss (ablation)DPL · VCDPSNR (dB): 24.81 -> 25.27Improved
use Lpsl instead of triplet loss (ablation)DPL · VCDPSNR (dB): 24.03 -> 25.27Improved
use Lpsl instead of center loss (ablation)DPL · VCDPSNR (dB): 23.08 -> 25.27Improved
dual-level prototype scene embeddings vs OneRestore fixed text embeddings (ablation)OneRestore · CDD-11PSNR (dB): 28.47 -> 29.55Improved
replace Lpsl with contrastive loss (SSIM) (ablation)DPL · VCDSSIM: 0.802 -> 0.799Hurt

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