AI Paper Atlas

Research map / Image generation / Image restoration

Towards a Universal Image Degradation Model via Content-Degradation Disentanglement

Wenbo Yang, Zhongling Wang, Zhou Wang

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 entropy regularization (disentangle-by-compression) (ablation)degradation model · FFHQ-X Mixed transferLPIPS: .334 -> .286Improved
add entropy regularization (disentangle-by-compression) (ablation)degradation model · FFHQ-X Direct transferLPIPS: .290 -> .271Improved
add IDA layer (ablation)degradation model · FFHQ-X Mixed transferLPIPS: .356 -> .286Improved
add IDA layer (ablation)degradation model · FFHQ-X Direct transferLPIPS: .298 -> .271Improved
add IDA layer (ablation)degradation model · FFHQ-X Global-only transferLPIPS: .404 -> .388Improved
add IDEN on top of IDA-less model (ablation)degradation model · FFHQ-X Direct transferLPIPS: .577 -> .298Improved
add IDEN on top of IDA-less model (ablation)degradation model · FFHQ-X Global-only transferLPIPS: .394 -> .404No clear effect
plug our degradation model into blind RSG GAN inversionRSG · FFHQ-X NAaccuracy (LPIPS): .680 -> .513Improved
plug our degradation model into blind RSG GAN inversionRSG · FFHQ-X UNAPrealism (pFID): 147.4 -> 31.7Improved
plug our degradation model into blind RSG GAN inversionRSG · FFHQ-X UAaccuracy (LPIPS): .519 -> .512No clear effect
transfer degradation instead of reproducedegradation model · synthetic WQILPIPS: 0.295 -> 0.306No clear effect
use universal model instead of specialized film grain baselinedegradation model · FilmGrainStylereproduction scoreImproved

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