Research map / Image generation / Image restoration
Cycle-CNN for Colorization towards Real Monochrome-Color Camera Systems
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 |
|---|---|---|---|
| add cycle consistency loss (ablation) | Cycle CNN · Real Dataset | SSIM: 0.8140 -> 0.9547 | Helped |
| add learned structure similarity loss (ablation) | Cycle CNN · Real Dataset | SSIM: 0.9192 -> 0.9547 | Helped |
| add spatial smoothness loss (ablation) | Cycle CNN · Real Dataset | SSIM: 0.9432 -> 0.9547 | Helped |
| use learned structure similarity loss instead of plain SSIM (ablation) | Cycle CNN · Real Dataset | SSIM: 0.9236 -> 0.9547 | Helped |
| train on real data with cycle CNN instead of synthesized-data training (Dong et al.) | colorization CNN · Real Dataset | SSIM: 0.871 -> 0.954 | Helped |
| Cycle CNN versus Dong et al. on synthesized datasets | colorization CNN · Cityscapes/Middlebury/Sintel/SceneFlow | SSIM (first-time): 0.982 -> 0.983 (Cityscapes) | Helped |
Closest papers by meaning
- Learning a Deep Convolutional Network for Colorization in Monochrome-Color Dual-Lens System (AAAI 2019 · similarity 0.90)
- Colorization Transformer (ICLR 2021 · similarity 0.86)
- Generative Quanta Color Imaging (CVPR 2024 · similarity 0.83)
- Automatic Controllable Colorization via Imagination (CVPR 2024 · similarity 0.82)
- Color-Oriented Redundancy Reduction in Dataset Distillation (NeurIPS 2024 · similarity 0.82)
- Efficient Neural Network Encoding for 3D Color Lookup Tables (AAAI 2025 · 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.