AI Paper Atlas

Research map / Image generation / Image restoration

CLEARER: Multi-Scale Neural Architecture Search for Image Restoration

Yuanbiao Gou, Boyun Li, Zitao Liu, Songfan Yang, Xi Peng

NeurIPS 2020 · Image generation › Image restoration · approach: Priors for restoration networks · 50 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 architecture loss (lambda1 0.00 -> 0.01) (ablation)CLEARER · BSD500 sigma=30PSNR: 28.51 -> 28.54Improved
raise architecture loss weight lambda1 0.01 -> 0.10 (ablation)CLEARER · BSD500 sigma=30PSNR: 28.54 -> 28.53No clear effect
add complexity loss (lambda2 0 -> 0.01) (ablation)CLEARER · BSD500 sigma=30PSNR: 28.54 -> 28.33Hurt
add complexity loss (lambda2 0 -> 0.01) (ablation)CLEARER · BSD500 sigma=30parameters (M): 6.31 -> 4.59Improved
replace differentiable search with random architecture (ablation)CLEARER · BSD500 sigma=30PSNR: 28.29 -> 28.54Improved
add architecture loss lambda1 0.00 -> 0.01 (ablation)CLEARER · BSD500 sigma=30parameters (M): 7.25 -> 6.31Improved
add architecture loss lambda1 0.00 -> 0.01 (ablation)CLEARER · BSD500 sigma=30testing time (s): 4.28 -> 5.28Hurt

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