Research map / Image generation / Image restoration
Image Inpainting With External-Internal Learning and Monochromic Bottleneck
Tengfei Wang, Hao Ouyang, Qifeng Chen
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 |
|---|---|---|---|
| Apply the external-internal monochromic bottleneck scheme | GatedConv · Places2 | PSNR: 23.94 -> 24.58 | Improved |
| Apply the external-internal monochromic bottleneck scheme | GatedConv · Paris StreetView | PSNR: 26.32 -> 26.75 | Improved |
| Apply the external-internal monochromic bottleneck scheme | GatedConv · CelebA-HQ | PSNR: 27.36 -> 27.51 | Improved |
| Apply the external-internal monochromic bottleneck scheme | HiFill · DTD | PSNR: 29.14 -> 29.38 | Improved |
| Add progressive restoration to internal colorization (ablation) | Ours internal color restoration · Places2 rectangular masks | PSNR: 37.04 -> 38.45 | Improved |
| Add progressive restoration to internal colorization (ablation) | Ours internal color restoration · Places2 irregular masks | PSNR: 39.21 -> 39.50 | Improved |
| Remove progressive restoration (ablation) | Ours internal color restoration · Inpainted monochromic bottleneck | colorization artifacts | Hurt |
| Use the monochromic bottleneck for cross-dataset reconstruction | Inpainting models trained on Places2 · CelebA-HQ cross-dataset evaluation | PSNR: 27.35 -> 27.38 | No clear effect |
Closest papers by meaning
- Internal Video Inpainting by Implicit Long-Range Propagation (ICCV 2021 · similarity 0.88)
- An Internal Learning Approach to Video Inpainting (ICCV 2019 · similarity 0.88)
- Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency (CVPR 2025 · similarity 0.88)
- StructureFlow: Image Inpainting via Structure-Aware Appearance Flow (ICCV 2019 · similarity 0.88)
- Contextual-based Image Inpainting: Infer, Match, and Translate (ECCV 2018 · similarity 0.87)
- Paint by Inpaint: Learning to Add Image Objects by Removing Them First (CVPR 2025 · 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.
