AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Retinex-Inspired Unrolling With Cooperative Prior Architecture Search for Low-Light Image Enhancement

Risheng Liu, Long Ma, Jiaao Zhang, Xin Fan, Zhongxuan Luo

CVPR 2021 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 1,031 citations (OpenAlex)

Check 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
Use RUAS instead of DeepUPELow-light enhancement · MIT-Adobe 5KPSNR: 18.779 -> 20.830Improved
Use RUAS instead of LIMELow-light enhancement · MIT-Adobe 5KSSIM: 0.826 -> 0.854Improved
Use RUAS instead of FIDELow-light enhancement · LOLPSNR: 16.718 -> 18.226Improved
Use RUAS instead of DRBNLow-light enhancement · LOLSSIM: 0.699 -> 0.717Improved
Add residual rectification to the updating warm-start strategy (ablation)RUAS illumination estimation · Low-light image enhancementexposure qualityImproved
Update the warm-start illumination rather than keeping it fixed (ablation)RUAS illumination estimation · Low-light image enhancementoverexposure suppressionImproved
Add the noise removal module (NRM) (ablation)RUAS_i · Noisy low-light imagesimage qualityImproved
Search the architecture instead of using manually determined architectures (ablation)RUAS · MIT-Adobe 5KPSNRImproved
Use cooperative search instead of separate or naive joint search (ablation)RUAS IEM and NRM · Low-light image enhancementnumerical scoresImproved

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