Research map / Image generation / Image restoration
Representative Color Transform for Image Enhancement
Hanul Kim, Su-Min Choi, Chang-Su Kim, Yeong Jun Koh
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 global RCT (ablation) | RCTNet · MIT-Adobe 5K | PSNR (dB): 25.43 -> 26.02 | Improved |
| add global RCT (ablation) | RCTNet · EUVP | PSNR (dB): 24.30 -> 26.43 | Improved |
| add local RCT (ablation) | RCTNet · MIT-Adobe 5K | PSNR (dB): 25.57 -> 26.02 | Improved |
| add local RCT (ablation) | RCTNet · EUVP | PSNR (dB): 24.46 -> 26.43 | Improved |
| add feature fusion (ablation) | RCTNet · MIT-Adobe 5K | PSNR (dB): 25.68 -> 26.02 | Improved |
| add feature fusion (ablation) | RCTNet · LoL | PSNR (dB): 22.30 -> 22.67 | Improved |
| add feature fusion (ablation) | RCTNet · EUVP | PSNR (dB): 25.19 -> 26.43 | Improved |
| replace encoder-decoder with global RCT (ablation) | enhancement head · MIT-Adobe 5K | PSNR (dB): 24.26 -> 25.57 | Improved |
| replace encoder-decoder with global RCT (ablation) | enhancement head · LoL | PSNR (dB): 21.25 -> 22.35 | Mixed |
| replace global intensity transform with global RCT (ablation) | enhancement head · MIT-Adobe 5K | PSNR (dB): 24.97 -> 25.57 | Improved |
| replace global intensity transform with global RCT (ablation) | enhancement head · LoL | PSNR (dB): 21.20 -> 22.35 | Improved |
| add bilateral filter post-processing | RCTNet · MIT-Adobe 5K | SSIM: 0.915 -> 0.923 | Improved |
Closest papers by meaning
- Color Shift Estimation-and-Correction for Image Enhancement (CVPR 2024 · similarity 0.85)
- GenColor: Generative and Expressive Color Enhancement with Pixel-Perfect Texture Preservation (NeurIPS 2025 · similarity 0.84)
- Real-Time Exposure Correction via Collaborative Transformations and Adaptive Sampling (CVPR 2024 · similarity 0.84)
- Luminance-aware Color Transform for Multiple Exposure Correction (ICCV 2023 · similarity 0.84)
- High-Resolution Image Harmonization with Adaptive-Interval Color Transformation (NeurIPS 2024 · similarity 0.83)
- ChromaFusionNet (CFNet): Natural Fusion of Fine-Grained Color Editing (AAAI 2024 · similarity 0.82)
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.
