Research map / Image generation / Image restoration
Hierarchical Integration Diffusion Model for Realistic Image Deblurring
Zheng Chen, Yulun Zhang, Ding Liu, Bin Xia, Jinjin Gu, Linghe Kong, Xin Yuan
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 diffusion-generated prior with hierarchical integration to Restormer (ablation) | Restormer · GoPro (ablation setting) | PSNR (dB): 31.96 -> 32.24 | Improved |
| use multi-scale prior instead of single-scale prior (ablation) | HI-Diff · GoPro (ablation setting) | PSNR (dB): 32.00 -> 32.24 | Improved |
| jointly train diffusion model and Transformer in stage two (ablation) | HI-Diff · GoPro (ablation setting) | PSNR (dB): 30.73 -> 32.24 | Improved |
| single-scale prior guide versus no prior (ablation) | Restormer · GoPro (ablation setting) | PSNR (dB): 31.96 -> 32.00 | No clear effect |
| increase diffusion iterations from 1 to 8 (ablation) | HI-Diff · GoPro | PSNR (dB) | Improved |
| increase diffusion iterations beyond 8 (to 16, 32) (ablation) | HI-Diff · GoPro | PSNR (dB) | No clear effect |
| replace Restormer with HI-Diff | Restormer · GoPro | PSNR (dB): 32.92 -> 33.33 | Improved |
| replace Restormer with HI-Diff | Restormer · HIDE | PSNR (dB): 31.22 -> 31.46 | Improved |
| replace Stripformer with HI-Diff trained on RealBlur | Stripformer · RealBlur-J (trained on RealBlur) | PSNR (dB): 32.48 -> 33.70 | Improved |
| replace Stripformer with HI-Diff trained on RealBlur | Stripformer · RealBlur-R (trained on RealBlur) | PSNR (dB): 39.84 -> 41.01 | Improved |
| add diffusion prior to Restormer (ablation) | Restormer · GoPro (ablation setting) | FLOPs (G): 117.25 -> 125.47 | Hurt |
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.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 5 of 5 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
- BlurDM: A Blur Diffusion Model for Image Deblurring (NeurIPS 2025 · similarity 0.91)
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models (NeurIPS 2025 · similarity 0.90)
- Residual Denoising Diffusion Models (CVPR 2024 · similarity 0.88)
- A Modular Conditional Diffusion Framework for Image Reconstruction (NeurIPS 2024 · similarity 0.88)
- Residual Diffusion Deblurring Model for Single Image Defocus Deblurring (AAAI 2025 · similarity 0.88)
- Improving Diffusion-Based Image Restoration with Error Contraction and Error Correction (AAAI 2024 · similarity 0.88)
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.
