Research map / Image generation / Image restoration
MR. Illuminate: Zero-Shot Low-Light Image Enhancement with Diffusion Prior
Joshua Cho, Sara Aghajanzadeh, Zhen Zhu, David Forsyth
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 |
|---|---|---|---|
| inject self-attention only in up-blocks (vs none) (ablation) | MR. Illuminate · qualitative ablation on LOL images | reconstruction fidelity | Improved |
| inject self-attention in all Down, Mid and Up blocks (ablation) | MR. Illuminate · qualitative ablation on LOL images | reconstruction fidelity | Hurt |
| inject self-attention in mid-block only (ablation) | MR. Illuminate · qualitative ablation on LOL images | reconstruction fidelity | No clear effect |
| inject cross-attention features instead of self-attention (ablation) | MR. Illuminate · qualitative ablation on LOL images | reconstruction fidelity | No clear effect |
| add self-attention injection from inversion (vs w/o SA) (ablation) | MR. Illuminate · qualitative ablation on LOL images | structure and color fidelity | Improved |
| add AdaIN modulation of the inverted latent to N(0,I) statistics (ablation) | MR. Illuminate · qualitative ablation | illumination and color constancy | Improved |
| use zero-shot MR. Illuminate instead of supervised CIDNet trained on a different dataset | CIDNet · LOL | PSNR: CIDNet LOLv1 28.9198 vs MIT5K 12.0433; MR. Illuminate 21.7393 | Mixed |
Closest papers by meaning
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.91)
- QuadPrior++: Multi-Dimension Augmented Physical Prior for Zero-Reference Illumination Enhancement (TPAMI 2025 · similarity 0.89)
- Empowering Low-Light Image Enhancer through Customized Learnable Priors (ICCV 2023 · similarity 0.88)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.88)
- Zero-Reference Low-Light Enhancement via Physical Quadruple Priors (CVPR 2024 · similarity 0.87)
- Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement (NeurIPS 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.
