Research map / Image generation / Image restoration
Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations
Tomáš Chobola, Yu Liu, Hanyi Zhang, Julia A Schnabel, Tingying Peng
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 sparsity loss L_spa (ablation) | CoLIE · MIT (200-image subset) | PSNR: 7.2470 -> 18.6703 | Improved |
| add illumination smoothness loss L_s (ablation) | CoLIE · MIT (200-image subset) | PSNR: 17.3028 -> 18.6703 | Improved |
| add exposure loss L_exp (ablation) | CoLIE · MIT (200-image subset) | PSNR: 15.5348 -> 18.6703 | Improved |
| add exposure loss L_exp (ablation) | CoLIE · MIT (200-image subset) | SSIM: 0.8132 -> 0.8317 | Mixed |
| increase context window size from 1x1 up to 7x7 (ablation) | CoLIE · DarkFace example image | illumination estimate quality (qualitative) | Improved |
| lower exposure target L in exposure loss (ablation) | CoLIE · DarkFace example image | brightness (qualitative) | Mixed |
| use zero-shot CoLIE instead of pretrained CNN enhancers on MIT | low-light enhancement · MIT (200-image subset) | PSNR: 17.0284 -> 18.6703 (vs best baseline HWMNet) | Improved |
| use CoLIE instead of SCI-difficult on UHD-LL | low-light enhancement · UHD-LL test set | PSNR: 17.8476 -> 17.8927 | No clear effect |
| enhance DarkFace images with CoLIE before Grounding DINO person detection | Grounding DINO · DarkFace | detected persons (qualitative) | 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.
- DeepLPF — DeepLPF: Deep Local Parametric Filters for Image Enhancement (CVPR 2020) · better on 1 of 1 shared result
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
- Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network (ICCV 2023 · similarity 0.88)
- Implicit Neural Representation for Cooperative Low-light Image Enhancement (ICCV 2023 · similarity 0.88)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.86)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.85)
- Zero-Reference Low-Light Enhancement via Physical Quadruple Priors (CVPR 2024 · similarity 0.85)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.85)
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.
