Research map / Image generation / Image restoration
Learning Multi-Scale Photo Exposure Correction
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 the coarse-to-fine multi-scale exposure correction model | Exposure correction on overexposed and properly exposed test images · Overexposed and properly exposed test images | PSNR (Avg.): 17.627 -> 19.198 | Helped |
| Use the coarse-to-fine multi-scale exposure correction model | Exposure correction on underexposed test images · Underexposed test images | PSNR (Avg.): 19.720 -> 19.646 | Hurt |
| Use the coarse-to-fine multi-scale exposure correction model | Exposure correction on combined over- and underexposed test images · Combined over- and underexposed test images | PSNR (Avg.): 17.890 -> 19.377 | Helped |
| Add pyramid loss to supervise intermediate scale outputs (ablation) | Four-level exposure correction model · 500-image validation subset | PSNR: 18.041 -> 18.385 | Helped |
| Use four Laplacian pyramid levels instead of one (ablation) | Exposure correction network · 500-image validation subset | PSNR: 16.984 -> 18.385 | Helped |
| Use four Laplacian pyramid levels instead of two (ablation) | Exposure correction network · 500-image validation subset | PSNR: 17.442 -> 18.385 | Helped |
| Add adversarial loss (ablation) | Exposure correction model · Overexposed and properly exposed test images | PI: 2.189 -> 2.183 | Helped |
| Add adversarial loss (ablation) | Exposure correction model · Overexposed and properly exposed test images | PSNR (Avg.): 19.349 -> 19.198 | Hurt |
| Add adversarial loss (ablation) | Exposure correction model · Combined over- and underexposed test images | PI: 2.251 -> 2.247 | Helped |
| Add adversarial loss (ablation) | Exposure correction model · Combined over- and underexposed test images | PSNR (Avg.): 19.483 -> 19.377 | Hurt |
Closest papers by meaning
- Exposure Normalization and Compensation for Multiple-Exposure Correction (CVPR 2022 · similarity 0.90)
- Region-Aware Exposure Consistency Network for Mixed Exposure Correction (AAAI 2024 · 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 0.84)
- DPLUT: Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors (AAAI 2025 · similarity 0.84)
- Real-Time Exposure Correction via Collaborative Transformations and Adaptive Sampling (CVPR 2024 · similarity 0.83)
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.