Research map / Image generation / Image restoration
Underexposed Photo Enhancement Using Deep Illumination Estimation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use DeepUPE instead of HDRNet | Underexposed photo enhancement · Underexposed photo dataset test | PSNR: 26.33 -> 30.97 | Helped |
| use DeepUPE instead of HDRNet | Underexposed photo enhancement · Underexposed photo dataset test | SSIM: 0.743 -> 0.856 | Helped |
| use DeepUPE instead of HDRNet | Photo enhancement · MIT-Adobe FiveK | PSNR: 28.61 -> 30.80 | Helped |
| use DeepUPE instead of HDRNet | Photo enhancement · MIT-Adobe FiveK | SSIM: 0.866 -> 0.893 | Helped |
| add reconstruction loss to naive image-to-image regression (ablation) | DeepUPE · Underexposed photo dataset test | PSNR: 27.02 -> 28.97 | Helped |
| add reconstruction loss to naive image-to-image regression (ablation) | DeepUPE · MIT-Adobe FiveK | PSNR: 28.81 -> 29.41 | Helped |
| add smoothness loss to reconstruction-loss training (ablation) | DeepUPE · Underexposed photo dataset test | PSNR: 28.97 -> 30.03 | Helped |
| add smoothness loss to reconstruction-loss training (ablation) | DeepUPE · MIT-Adobe FiveK | PSNR: 29.41 -> 30.71 | Helped |
| add color loss to reconstruction-and-smoothness training (ablation) | DeepUPE · Underexposed photo dataset test | PSNR: 30.03 -> 30.97 | Helped |
| add color loss to reconstruction-and-smoothness training (ablation) | DeepUPE · MIT-Adobe FiveK | PSNR: 30.71 -> 30.80 | Helped |
Closest papers by meaning
- Learning Multi-Scale Photo Exposure Correction (CVPR 2021 · similarity 0.89)
- Color Shift Estimation-and-Correction for Image Enhancement (CVPR 2024 · similarity 0.86)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.85)
- DPLUT: Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors (AAAI 2025 · similarity 0.85)
- Zero-Reference Low-Light Enhancement via Physical Quadruple Priors (CVPR 2024 · similarity 0.84)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 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.