Research map / Image generation / Image restoration
An Integrated Enhancement Solution for 24-Hour Colorful Imaging
Feifan Lv, Yinqiang Zheng, Yicheng Li, Feng Lu
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 SSIM loss to MAE loss (ablation) | Proposed imaging model · VNM test dataset | PSNR: 18.71 -> 19.12 | Improved |
| Add smoothness loss to MAE and SSIM losses (ablation) | Proposed imaging model · VNM test dataset | PSNR: 19.12 -> 19.54 | Improved |
| Add smoothness loss to MAE and SSIM losses (ablation) | Proposed imaging model · VNM test dataset | SSIM: 0.846 -> 0.839 | Hurt |
| Add perceptual loss to MAE, SSIM, and smoothness losses (ablation) | Proposed imaging model · VNM test dataset | PSNR: 19.54 -> 19.71 | Improved |
| Add perceptual loss to MAE, SSIM, and smoothness losses (ablation) | Proposed imaging model · VNM test dataset | SSIM: 0.839 -> 0.853 | Improved |
| Add Separation-Net to a model without Separation-Net or Restoration-Net (ablation) | Proposed imaging model · VNM test dataset | PSNR: 16.74 -> 18.88 | Improved |
| Add Restoration-Net to a model without Separation-Net or Restoration-Net (ablation) | Proposed imaging model · VNM test dataset | PSNR: 16.74 -> 17.06 | Improved |
| Add Restoration-Net to the model with Separation-Net (ablation) | Proposed imaging model · VNM test dataset | PSNR: 18.88 -> 19.71 | Improved |
| Double Colorization-Net output size (ablation) | Proposed imaging model · VNM test dataset | PSNR: 19.71 -> 19.10 | Hurt |
| Replace YUV with HSV color space (ablation) | Proposed imaging model · VNM test dataset | PSNR: 19.71 -> 18.30 | Hurt |
| Replace YUV with RGB color space (ablation) | Proposed imaging model · VNM test dataset | PSNR: 19.71 -> 17.58 | Hurt |
Closest papers by meaning
- NIR-assisted Video Enhancement via Unpaired 24-hour Data (ICCV 2023 · similarity 0.88)
- Learn to Recover Visible Color for Video Surveillance in a Day (ECCV 2020 · similarity 0.87)
- Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning (CVPR 2024 · similarity 0.82)
- Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images (AAAI 2025 · similarity 0.81)
- Color Shift Estimation-and-Correction for Image Enhancement (CVPR 2024 · similarity 0.81)
- Unveiling Details in the Dark: Simultaneous Brightening and Zooming for Low-Light Image Enhancement (AAAI 2024 · similarity 0.81)
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.
