Research map / Image generation / Image restoration
Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration
Luwei Tu, Jiawei Wu, Xing Luo, Zhi Jin
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 uncertainty-aware path schedule instead of OT schedule pi(u)=I (ablation) | UDBM-L · All-in-One average | PSNR: 32.31 -> 32.61 | Improved |
| use adaptive path schedule instead of pi(u)=0.5I (ablation) | UDBM-L · All-in-One average | PSNR: 32.02 -> 32.61 | Improved |
| add adaptive shared bridge term instead of constant 1.5 lambda_b (ablation) | UDBM-L · All-in-One average | PSNR: 31.62 -> 32.61 | Improved |
| add terminal relaxation term (ablation) | UDBM-L · All-in-One average | PSNR: 30.72 -> 32.61 | Improved |
| use uncertainty-adaptive relaxation instead of fixed 1.5I (ablation) | UDBM-L · All-in-One average | PSNR: 32.12 -> 32.61 | Improved |
| use residual-based estimator instead of BayesCap (ablation) | UDBM-L · All-in-One average | PSNR: 32.46 -> 32.61 | Improved |
| use residual-based estimator instead of heteroscedastic regression (ablation) | UDBM-L · All-in-One average | PSNR: 32.04 -> 32.61 | Improved |
| use UDBM-M instead of HOGformer | UDBM-M · All-in-One average | PSNR: 31.57 -> 31.60 | Improved |
| use UDBM-L instead of BioIR on denoising | UDBM-L · BSD68 | PSNR: 31.34 -> 31.40 | Improved |
| use UDBM-L instead of NAFNet | UDBM-L · GoPro | PSNR: 33.69 -> 33.87 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- AdaIR — AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation (ICLR 2025) · better on 2 of 2 shared results
- Prompt-IR — PromptIR: Prompting for All-in-One Image Restoration (NeurIPS 2023) · better on 2 of 2 shared results
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 2 of 2 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
- UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control (ICML 2025 · similarity 0.91)
- Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge (ICML 2024 · similarity 0.89)
- Exploring the Design Space of Diffusion Bridge Models (NeurIPS 2025 · similarity 0.88)
- IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models (ICML 2025 · similarity 0.88)
- DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration (NeurIPS 2025 · similarity 0.87)
- Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model (CVPR 2025 · similarity 0.87)
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.
