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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add mask extractor and cooperative loss to the naive dual loop (ablation) | NeRCo dual loop · LSRW | PSNR: 16.77 -> 17.65 | Improved |
| add text-driven appearance discriminator (TAD) (ablation) | NeRCo without NRN · LSRW | PSNR: 17.65 -> 18.32 | Improved |
| add neural representation normalization (NRN) (ablation) | NeRCo without TAD · LSRW | PSNR: 17.65 -> 18.62 | Improved |
| add both NRN and TAD (full NeRCo) (ablation) | NeRCo with CL&ME · LSRW | PSNR: 18.62 -> 19.00 | Improved |
| add TAD to NeRCo with NRN (ablation) | NeRCo · LSRW | NIQE: 9.63 -> 9.23 | Improved |
| add edge path to color-path discriminator (ablation) | TAD · LSRW | PSNR: 17.37 -> 17.65 | Improved |
| add text supervision to color+edge discriminator (ablation) | TAD · LSRW | PSNR: 17.65 -> 18.32 | Improved |
| add text supervision to color+edge discriminator (ablation) | TAD · LSRW | NIQE: 10.60 -> 10.83 | Hurt |
| replace prompts low-light/high-light with synonyms (dark/bright, dim/light, night/day) (ablation) | NeRCo without NRN · LSRW | PSNR: 18.32 -> 18.58 / 18.23 / 18.56 | No clear effect |
| unsupervised NeRCo versus supervised baselines | NeRCo · LOL | PSNR: 19.54 -> 19.84 | Improved |
| NeRCo versus SCI on a no-reference metric | NeRCo · LOL | LOE: 102.3 vs 117.7 | Hurt |
| text-driven discrimination yields semantically better outputs than reference images | NeRCo · LOL | CLIP semantic score: 0.5910 -> 0.6366 | Improved |
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.
- URetinexNet — URetinex-Net: Retinex-Based Deep Unfolding Network for Low-Light Image Enhancement (CVPR 2022) · better on 4 of 5 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
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.89)
- Empowering Low-Light Image Enhancer through Customized Learnable Priors (ICCV 2023 · similarity 0.88)
- Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images (AAAI 2025 · similarity 0.86)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.86)
- Zero-Reference Low-Light Enhancement via Physical Quadruple Priors (CVPR 2024 · similarity 0.86)
- Improving Visual and Downstream Performance of Low-Light Enhancer with Vision Foundation Models Collaboration (CVPR 2025 · similarity 0.86)
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.
