Research map / Image generation / Image restoration
Learning to See in the Dark
Read the paperCheck 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 raw-data U-net pipeline instead of BM3D | Low-light image processing · Sony x300 set | preference rate: 92.4% | Helped |
| Use the raw-data U-net pipeline instead of burst denoising | Low-light image processing · Sony x300 set | preference rate: 85.2% | Helped |
| Use the raw-data U-net pipeline instead of BM3D | Low-light image processing · Sony x100 set | preference rate: 59.3% | No clear effect |
| Use the raw-data U-net pipeline instead of burst denoising | Low-light image processing · Sony x100 set | preference rate: 47.3% | No clear effect |
| Replace U-net with CAN (ablation) | SID low-light pipeline · SID Sony | PSNR: 28.88 -> 27.40 | Hurt |
| Replace U-net with CAN (ablation) | SID low-light pipeline · SID Fuji | PSNR: 26.61 -> 25.71 | Hurt |
| Process traditional-pipeline sRGB instead of raw sensor data (ablation) | SID low-light pipeline · SID Sony | PSNR: 28.88 -> 17.40 | Hurt |
| Process traditional-pipeline sRGB instead of raw sensor data (ablation) | SID low-light pipeline · SID Fuji | PSNR: 26.61 -> 25.11 | Hurt |
| Replace L1 loss with SSIM loss (ablation) | SID low-light pipeline · SID Sony | PSNR: 28.88 -> 28.64 | No clear effect |
| Replace L1 loss with L2 loss (ablation) | SID low-light pipeline · SID Sony | PSNR: 28.88 -> 28.47 | No clear effect |
| Replace L1 loss with SSIM loss (ablation) | SID low-light pipeline · SID Fuji | PSNR: 26.61 -> 26.20 | No clear effect |
| Replace L1 loss with L2 loss (ablation) | SID low-light pipeline · SID Fuji | PSNR: 26.61 -> 26.51 | No clear effect |
Closest papers by meaning
- Contrastive Learning for Low-Light Raw Denoising (Student Abstract) (AAAI 2024 · similarity 0.89)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.88)
- DarkIR: Robust Low-Light Image Restoration (CVPR 2025 · similarity 0.88)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.87)
- DPLUT: Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors (AAAI 2025 · similarity 0.87)
- FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network (NeurIPS 2025 · similarity 0.87)
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.