Research map / Image generation / Image restoration
Deeply Aggregated Alternating Minimization for 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 three AM iterations rather than one or two (ablation) | DeepAM · BSD68 denoising, σ=15, 25, and 50 | PSNR: 31.40 -> 31.68; 31.65 -> 31.68; 28.95 -> 29.21; 29.18 -> 29.21; 25.94 -> 26.24; 26.20 -> 26.24 | Helped |
| Replace point-wise proximal mapping with learned deep aggregation | DeepAM · Single-image denoising | PSNR: +0.3~0.5dB | Helped |
| Use DeepAM(3) instead of the strongest listed baseline | BSD68 denoising · σ=15, 25, and 50 | PSNR: 31.42 -> 31.68; 28.91 -> 29.21; 26.00 -> 26.24 | Helped |
| Use DeepAM(2) instead of the strongest listed baseline | Depth super-resolution · NYU v2 and Middlebury, ×4, ×8, and ×16 | BMP (δ=3): 0.68 -> 0.57; 2.41 -> 3.14; 1.92 -> 1.58; 5.97 -> 5.78; 5.82 -> 4.63; 12.18 -> 10.45 | Mixed |
| Use DeepAM(2) instead of the strongest listed baseline | RGB/NIR restoration · Five-pair average, σ=50 | PSNR: 28.28 -> 29.28 | Helped |
| Concatenate guidance halfway through feature extraction rather than at the input (ablation) | Joint-restoration DeepAM · Joint restoration | restoration effectiveness | Helped |
Closest papers by meaning
- End-to-End Learning for Joint Image Demosaicing, Denoising and Super-Resolution (CVPR 2021 · similarity 0.87)
- Deep Generalized Unfolding Networks for Image Restoration (CVPR 2022 · similarity 0.87)
- A Restoration Network as an Implicit Prior (ICLR 2024 · similarity 0.87)
- Debiased All-in-one Image Restoration with Task Uncertainty Regularization (AAAI 2025 · similarity 0.85)
- Proximal Algorithm Unrolling: Flexible and Efficient Reconstruction Networks for Single-Pixel Imaging (CVPR 2025 · similarity 0.85)
- Stochastic Deep Restoration Priors for Imaging Inverse Problems (ICML 2025 · similarity 0.85)
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.