AI Paper Atlas

Research map / Image generation / Image restoration

Context-Aware Pretraining for Efficient Blind Image Decomposition

Chao Wang, Zhedong Zheng, Ruijie Quan, Yifan Sun, Yi Yang

CVPR 2023 · Image generation › Image restoration · approach: Priors for restoration networks · 28 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 separation encoder EA (ablation)CPNet · Task II, rainstreak + raindrop + snowPSNR: 18.25 -> 28.57Improved
add the reconstruction encoder EB (ablation)CPNet · Task II, rainstreak + raindrop + snowPSNR: 21.36 -> 28.57Improved
add the feature interaction block (ablation)CPNet · Task II, rainstreak + raindrop + snowPSNR: 25.84 -> 28.57Improved
add the feature refinement block (ablation)CPNet · Task II, rainstreak + raindrop + snowPSNR: 27.23 -> 28.57Improved
add the feature enhancement block (ablation)CPNet · Task II, rainstreak + raindrop + snowPSNR: 27.47 -> 28.57Improved
add conditional attribute loss (ablation)CPNet · Task II, rainstreak + raindrop + snowPSNR: 28.29 -> 28.57Improved
pretrain on ImageNet instead of the BID dataset (ablation)CPNet · Task I case (5)PSNR: 26.80 -> 30.07Improved
pretrain on a broader set of ImageNet classes rather than only selected scene classes (ablation)CPNet · Task I case (5)PSNR: 28.43 -> 30.07Improved
pretrain on scene-relevant rather than selected irrelevant object classes (ablation)CPNet · Task I case (5)PSNR: 24.89 -> 28.43Improved
use 10% of ImageNet rather than the full ImageNet pretraining set (ablation)CPNet · Task I case (5)PSNR: 30.07 -> 28.95Hurt
use CPNet rather than BIDeNblind image decomposition · CityScape Task I, case (6)PSNR: 26.44 -> 29.57Improved
use CPNet rather than BIDeN for single-noise restoration after multi-noise trainingBID models · Task II, raindropBRISQUE: 21.22 -> 20.16Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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