Research map / Image generation / Image restoration
Deep Edge-Aware Interactive Colorization Against Color-Bleeding Effects
Eungyeup Kim, Sanghyeon Lee, Jeonghoon Park, Somi Choi, Choonghyun Seo, Jaegul Choo
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 edge-enhancing network with user scribbles | Zhang et al. (conditional) · ImageNet ctest10k local kernel 7 | PSNR: 14.966 -> 16.041 | Improved |
| add edge-enhancing network with user scribbles | Zhang et al. (conditional) · ImageNet ctest10k local kernel 7 | LPIPS: 0.208 -> 0.177 | Improved |
| add edge-enhancing network with user scribbles | Su et al. (conditional) · ImageNet ctest10k local kernel 7 | PSNR: 16.393 -> 16.507 | Improved |
| add edge-enhancing network with user scribbles | Zhang et al. (unconditional) · ImageNet ctest10k full image | PSNR: 21.981 -> 22.026 | No clear effect |
| add edge-enhancing network with user scribbles | Zhang et al. (conditional) · ImageNet ctest10k | cluster discrepancy ratio: 0.418 -> 0.543 | Improved |
| add edge-enhancing network with user scribbles | Su et al. (conditional) · ImageNet ctest10k | cluster discrepancy ratio: 0.336 -> 0.394 | Improved |
| add consistency loss L_con (ablation) | edge-enhancing network · ImageNet ctest10k ablation | PSNR: 15.799 -> 16.041 | Improved |
| add consistency loss L_con (ablation) | edge-enhancing network · ImageNet ctest10k ablation | cluster discrepancy ratio: 0.472 -> 0.512 | Mixed |
| add regularization loss L_reg (ablation) | edge-enhancing network · ImageNet ctest10k ablation | PSNR: 15.624 -> 16.041 | Improved |
| add regularization loss L_reg (ablation) | edge-enhancing network · ImageNet ctest10k ablation | cluster discrepancy ratio: 0.605 -> 0.512 | Hurt |
| add scribble width augmentation (ablation) | edge-enhancing network · ImageNet ctest10k ablation | PSNR: 13.372 -> 16.041 | Improved |
| add scribble width augmentation (ablation) | edge-enhancing network · ImageNet ctest10k ablation | LPIPS: 0.259 -> 0.177 | Improved |
Closest papers by meaning
- PalGAN: Image Colorization with Palette Generative Adversarial Networks (ECCV 2022 · similarity 0.88)
- DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders (ICCV 2023 · similarity 0.88)
- Colorful Image Colorization (ECCV 2016 · similarity 0.87)
- Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization (ECCV 2026 · similarity 0.87)
- Enabling Region-Specific Control via Lassos in Point-Based Colorization (AAAI 2025 · similarity 0.86)
- Automatic Controllable Colorization via Imagination (CVPR 2024 · similarity 0.86)
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.
