Research map / Image generation / Image restoration
Beyond Illumination: Fine-Grained Detail Preservation in Extreme Dark Image Restoration
Tongshun Zhang, Pingping Liu, Zixuan Zhong, Zijian Zhang, Qiuzhan Zhou
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 the frequency-domain first stage (RFGM stage) (ablation) | dual-stage model · ablation | PSNR: 20.73 -> 21.59 | Improved |
| add the spatial-domain second stage (ablation) | dual-stage model · ablation | PSNR: 20.95 -> 21.59 | Improved |
| add RFGM (ablation) | dual-stage model · ablation | PSNR: 21.24 -> 21.59 | Improved |
| add Grad Mamba (ablation) | dual-stage model · ablation | PSNR: 21.21 -> 21.59 | Improved |
| add Patch Mamba (ablation) | dual-stage model · ablation | PSNR: 21.54 -> 21.59 | Improved |
| add RFGM to FourLLIE | FourLLIE · Plug-and-play | PSNR: 21.11 -> 21.39 | Improved |
| add RFGM and Patch SS2D to DMFourLLIE | DMFourLLIE · Plug-and-play | PSNR: 21.47 -> 21.52 | Improved |
| use 16 Patch SS2D patches instead of 1 (ablation) | Patch Mamba · efficiency | computation time: 0.346s -> 0.181s | Improved |
| restoration with the method vs baselines on unsupervised DICM and VV | full method · DICM, VV | exposure suppression | Hurt |
| restore with the method before text detection | CRAFT and PAN detectors · LOL-Text | H-Mean: PAN 0.1880 -> 0.2350 (vs MambaLLIE) | Improved |
| method vs CIDNet on LOL-v1 SSIM | full method · LOL-v1 | SSIM: 0.8574 -> 0.8517 | Hurt |
Closest papers by meaning
- From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective (CVPR 2025 · similarity 0.87)
- MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration (CVPR 2025 · similarity 0.86)
- VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook (AAAI 2024 · similarity 0.85)
- Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring (CVPR 2024 · similarity 0.84)
- Low-Light Face Super-resolution via Illumination, Structure, and Texture Associated Representation (AAAI 2024 · similarity 0.84)
- Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement (NeurIPS 2025 · similarity 0.84)
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.
