Research map / Image generation / Image restoration
OneRestore: A Universal Restoration Framework for Composite Degradation
Yu Guo, Yuan Gao, Yuxu Lu, Huilin Zhu, Wen Liu, Shengfeng He
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 scene-descriptor cross-attention (SDCA) to SA + FFN (ablation) | OneRestore · CDD-11 test | PSNR: 27.19 -> 28.72 | Improved |
| add self-attention to SDCA + FFN (ablation) | OneRestore · CDD-11 test | PSNR: 27.93 -> 28.72 | Improved |
| replace SA with SDCA in the transformer block (ablation) | OneRestore · CDD-11 test | PSNR: 27.19 -> 27.93 | Improved |
| use composite degradation restoration loss (CDRL) instead of ordinary contrastive loss (ablation) | OneRestore · CDD-11 test | PSNR: 27.61 -> 28.72 | Improved |
| add ordinary contrastive loss (ablation) | OneRestore · CDD-11 test | PSNR: 27.54 -> 27.61 | No clear effect |
| add MS-SSIM loss to smooth l1 (ablation) | OneRestore · CDD-11 test | PSNR: PSNR 28.16 -> 27.54; SSIM 0.8633 -> 0.8708 | Mixed |
| use text embedder (manual) instead of visual embedder directly (ablation) | OneRestore · CDD-11 test | PSNR: 28.24 -> 28.72 | Improved |
| estimate text embedding from image via visual embedder instead of per-image visual embedding (ablation) | OneRestore · CDD-11 test | PSNR: 28.24 -> 28.47 | Improved |
| retrain universal OneRestore on single-degradation benchmarks | OneRestore · LOL, RESIDE-OTS, Rain1200 | PSNR: LOL 24.25 vs best 25.15; RESIDE-OTS 35.58 vs best 37.94 | Mixed |
Later papers that compared with this method
10 later accepted papers report OneRestore as a baseline in their results tables; 10 of them report a better number on most of the results they share with it.
- PRISM: Controllable Diffusion for Compound Image Restoration with Scientific Fidelity (ICLR 2026 · better on 2 of 2 shared results)
- Learning Where and What to Restore for Composite Image Restoration (NeurIPS 2026 · better on 2 of 2 shared results)
- All-in-One Transformer for Image Restoration Under Adverse Weather Degradations (TPAMI 2026 · better on 2 of 2 shared results)
- Rethinking Expressivity and Degradation-Awareness in Attention for All-in-One Blind Image Restoration (ICLR 2026 · better on 1 of 1 shared result)
- Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization (ICLR 2026 · better on 1 of 1 shared result)
- Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration (NeurIPS 2026 · better on 1 of 1 shared result)
- ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration (AAAI 2026 · better on 1 of 1 shared result)
- Dual-level Prototype Learning for Composite Degraded Image Restoration (ICCV 2025 · better on 8 of 8 shared results)
2 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 2 of 2 shared results
- PromptIR — PromptIR: Prompting for All-in-One Image Restoration (NeurIPS 2023) · better on 1 of 1 shared result
- Retinexformer — Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement (ICCV 2023) · better on 0 of 1 shared result
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
- All-in-One Transformer for Image Restoration Under Adverse Weather Degradations (TPAMI 2026 · similarity 0.92)
- A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends (TPAMI 2025 · similarity 0.91)
- Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration (CVPR 2026 · similarity 0.90)
- Learning Where and What to Restore for Composite Image Restoration (NeurIPS 2026 · similarity 0.89)
- Visual-Instructed Degradation Diffusion for All-in-One Image Restoration (CVPR 2025 · similarity 0.88)
- GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration (CVPR 2025 · 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.
