Research map / Image generation / Super-resolution
Ultra High-Resolution Image Inpainting with Patch-Based Content Consistency Adapter
Jianhui Zhang, Shen Cheng, Qirui Sun, Jia Liu, Wang Luyang, Chaoyu Feng, Chen Fang, Lei Lei, Jue Wang, Shuaicheng Liu
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 Reference Patch Adapter (ablation) | Patch-Adapter · High-resolution inpainting (2,000 images) | FID: 16.144 -> 14.594 | Improved |
| add Reference Patch Adapter (ablation) | Patch-Adapter · High-resolution inpainting (2,000 images) | Aesthetic score: 5.910 -> 6.021 | Improved |
| add Reference Patch Adapter (ablation) | Patch-Adapter · High-resolution inpainting (2,000 images) | LPIPS: 0.161 -> 0.153 | Improved |
| add Reference Patch Adapter (ablation) | Patch-Adapter · High-resolution inpainting (2,000 images) | CLIP Score: 26.8062 -> 26.8063 | No clear effect |
| add Dual Context Adapter to SDXL-inpainting (ablation) | SDXL-inpainting · OpenImages (random masks, global prompt) | FID: 13.326 -> 12.167 | Improved |
| add Dual Context Adapter to SDXL-inpainting (ablation) | SDXL-inpainting · OpenImages (random masks, global prompt) | CLIP Score: 26.268 -> 26.458 | Improved |
| add Dual Context Adapter to SDXL-inpainting (ablation) | SDXL-inpainting · OpenImages (random masks, global prompt) | LPIPS: 0.129 -> 0.128 | No clear effect |
| add Dual Context Adapter to SDXL-inpainting (ablation) | SDXL-inpainting · OpenImages (segmentation masks, local prompt) | FID: 9.565 -> 9.427 | Improved |
| add Dual Context Adapter to SDXL-inpainting (ablation) | SDXL-inpainting · OpenImages (segmentation masks, local prompt) | CLIP Score: 26.990 -> 27.002 | No clear effect |
| add Dual Context Adapter to SDXL-inpainting (ablation) | SDXL-inpainting · OpenImages (segmentation masks, local prompt) | LPIPS: 0.092 -> 0.089 | Improved |
| Patch-Adapter vs SDXL Inpainting full pipeline | SDXL-inpainting · High-resolution inpainting (2,000 images) | FID: 17.660 -> 14.594 | Improved |
| Patch-Adapter vs HD-Painter | HD-Painter · High-resolution inpainting (2,000 images) | LPIPS: 0.230 -> 0.153 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- HD-Painter — HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models (ICLR 2025) · better on 4 of 4 shared results
- BrushNet — BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion (ECCV 2024) · better on 4 of 4 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
- High-Resolution Image Inpainting Using Multi-Scale Neural Patch Synthesis (CVPR 2017 · similarity 0.91)
- HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models (ICLR 2025 · similarity 0.88)
- MTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting (CVPR 2025 · similarity 0.87)
- Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency (CVPR 2025 · similarity 0.87)
- EditBridge: Towards Faithful and Efficient Ultra-High-Resolution Image Editing (NeurIPS 2026 · similarity 0.87)
- CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility (AAAI 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.
