AI Paper Atlas

Research map / Image generation / Image restoration

Implicit Neural Representation for Cooperative Low-light Image Enhancement

Shuzhou Yang, Moxuan Ding, Yanmin Wu, Zihan Li, Jian Zhang

ICCV 2023 · Image generation › Image restoration · approach: Low-light image enhancement · 296 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 mask extractor and cooperative loss to the naive dual loop (ablation)NeRCo dual loop · LSRWPSNR: 16.77 -> 17.65Improved
add text-driven appearance discriminator (TAD) (ablation)NeRCo without NRN · LSRWPSNR: 17.65 -> 18.32Improved
add neural representation normalization (NRN) (ablation)NeRCo without TAD · LSRWPSNR: 17.65 -> 18.62Improved
add both NRN and TAD (full NeRCo) (ablation)NeRCo with CL&ME · LSRWPSNR: 18.62 -> 19.00Improved
add TAD to NeRCo with NRN (ablation)NeRCo · LSRWNIQE: 9.63 -> 9.23Improved
add edge path to color-path discriminator (ablation)TAD · LSRWPSNR: 17.37 -> 17.65Improved
add text supervision to color+edge discriminator (ablation)TAD · LSRWPSNR: 17.65 -> 18.32Improved
add text supervision to color+edge discriminator (ablation)TAD · LSRWNIQE: 10.60 -> 10.83Hurt
replace prompts low-light/high-light with synonyms (dark/bright, dim/light, night/day) (ablation)NeRCo without NRN · LSRWPSNR: 18.32 -> 18.58 / 18.23 / 18.56No clear effect
unsupervised NeRCo versus supervised baselinesNeRCo · LOLPSNR: 19.54 -> 19.84Improved
NeRCo versus SCI on a no-reference metricNeRCo · LOLLOE: 102.3 vs 117.7Hurt
text-driven discrimination yields semantically better outputs than reference imagesNeRCo · LOLCLIP semantic score: 0.5910 -> 0.6366Improved

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