AI Paper Atlas

Research map / Image generation / Super-resolution

Learning Degradation Representations for Image Deblurring

Dasong Li, Yi Zhang, Ka Chun Cheung, Xiaogang Wang, Hongwei Qin, Hongsheng Li

ECCV 2022 · Image generation › Super-resolution · approach: Blind super-resolution · 79 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 the learned degradation encoder and representations (ablation)Ours (deblurring generator) · GoPro testPSNR: 32.81 -> 33.28Improved
add joint reblurring generator for learning degradation representations (ablation)Ours · GoPro testPSNR: 33.09 -> 33.28Improved
add blur-aware loss (ablation)Ours · GoPro testPSNR: 33.21 -> 33.28Improved
inject degradation at multiple scales instead of only the lowest resolution (ablation)Ours · GoPro testPSNR: 32.80 -> 33.28Improved
use spatially adaptive modulation instead of concatenation at skip connections (ablation)Ours · GoPro testPSNR: 33.05 -> 33.28Improved
inject via skip-connection modulation instead of concatenating degradation map at the network input (ablation)Ours · GoPro testPSNR: 32.98 -> 33.28Improved
use learned degradation representations vs MPRNet-patch256 on blurriest 10% imagesOurs · GoPro test (blurriest 10%)PSNR: 29.31 -> 29.65Improved
use MSDI-Net with degradation representations vs MPRNet-patch256 computeOurs · GoPro testMACs (G): 760.11 -> 336.43Improved
apply degradation representations trained on GoPro directly to RealBlurOurs · RealBlur testPSNR: 32.12 -> 32.35Improved
use Ours instead of HINetHINet · GoPro testPSNR: 32.71 -> 33.28Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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