Research map / Image generation / Image restoration
CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying
Weihuang Liu, Xiaodong Cun, Chi-Man Pun, Menghan Xia, Yong Zhang, Jue Wang
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 |
|---|---|---|---|
| Use CoordFill instead of LaMa | high-resolution inpainting · Places2 2048×2048 | speed: 598ms -> 26ms | Improved |
| Use CoordFill instead of ZITS | high-resolution inpainting · Unsplash 1024×1024 | PSNR: 32.532 -> 33.093 | Improved |
| Use CoordFill instead of LaMa | high-resolution inpainting · CelebA-HQ 1024×1024 | PSNR: 26.098 -> 28.756 | Improved |
| Use CoordFill instead of ZITS | inpainting · Places2 1024×1024 | PSNR: 26.389 -> 26.322 | Hurt |
| Add masked-region-only supervision (ablation) | CoordFill with Pixel-Query · Places2 512×512 | PSNR: 26.0434 -> 26.2160 | Improved |
| Use Pixel-Query instead of a convolutional decoder (ablation) | CoordFill with masked prediction · Places2 512×512 | PSNR: 25.9557 -> 26.2160 | Improved |
| Use Pixel-Query instead of a shared MLP decoder (ablation) | CoordFill with masked prediction · Places2 512×512 | PSNR: 24.6480 -> 26.2160 | Improved |
| Add masked-region-only supervision (ablation) | CoordFill with D_Conv · Places2 512×512 | PSNR: 25.5420 -> 25.9557 | Improved |
| Add AttFFC instead of using ResFFC (ablation) | CoordFill with Pixel-Query and masked prediction · Places2 512×512 | PSNR: 26.2160 -> 26.3177 | Improved |
| Add resolution conditioning (ablation) | CoordFill with Pixel-Query and AttFFC · Places2 512×512 | PSNR: 26.3177 -> 26.3653 | Improved |
Later papers that compared with this method
1 later accepted paper reports Coordfill as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting (AAAI 2024 · better on 6 of 6 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ZITS — ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors (TPAMI 2023) · better on 2 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Rethinking Fast Fourier Convolution in Image Inpainting (ICCV 2023 · similarity 0.87)
- High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling (ECCV 2020 · similarity 0.86)
- Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World (CVPR 2024 · similarity 0.84)
- SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting (AAAI 2024 · similarity 0.84)
- Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model (NeurIPS 2024 · similarity 0.84)
- HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models (ICLR 2025 · similarity 0.83)
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.
