Research map / Image generation / Image restoration
Multi-Stage Progressive Image Restoration
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the three-stage MPRNet instead of MSPFN | Image deraining · Rain100L | PSNR: 32.40 -> 36.40 | Helped |
| Use MPRNet instead of the strongest listed baseline | Image deblurring · GoPro | PSNR: 31.85 -> 32.66 | Helped |
| Use MPRNet trained on GoPro directly on HIDE | Image deblurring · HIDE | PSNR: +0.98 dB | Helped |
| Use MPRNet instead of CycleISP | Image denoising · SIDD | PSNR: 39.52 -> 39.71 | Helped |
| Use MPRNet instead of SADNet | Image denoising · DND | PSNR: 39.59 -> 39.80 | Helped |
| Use complementary earlier encoder-decoder and final ORSNet stages rather than the same subnetwork design at every stage (ablation) | MPRNet · GoPro | PSNR: 29.4 dB; 29.53 dB -> 29.7 dB | Helped |
| Add a third stage to the two-stage U-Net + ORSNet arrangement (ablation) | MPRNet · GoPro | PSNR: 29.70 -> 29.86 | Helped |
| Add CSFF (ablation) | MPRNet · GoPro | PSNR: 29.86 -> 30.07 | Helped |
| Add SAM (ablation) | MPRNet · GoPro | PSNR: 29.86 -> 30.31 | Helped |
| Add both SAM and CSFF (ablation) | MPRNet · GoPro | PSNR: 29.86 -> 30.49 | Helped |
| Add a second stage to the one-stage MPRNet (ablation) | MPRNet · GoPro | PSNR: 30.43 -> 31.81 | Helped |
| Add a third stage to the two-stage MPRNet (ablation) | MPRNet · GoPro | PSNR: 31.81 -> 32.66 | Helped |
Closest papers by meaning
- Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration (NeurIPS 2026 · similarity 0.88)
- ReFIR: Grounding Large Restoration Models with Retrieval Augmentation (NeurIPS 2024 · similarity 0.87)
- Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts (NeurIPS 2024 · similarity 0.87)
- Boosting Image Restoration via Priors from Pre-trained Models (CVPR 2024 · similarity 0.87)
- UP-Restorer: When Unrolling Meets Prompts for Unified Image Restoration (AAAI 2025 · similarity 0.86)
- Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration (AAAI 2024 · 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.