Research map / Learning theory and algorithms / Matrix and tensor methods
When deep denoising meets iterative phase retrieval
Read the paperCheck 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 |
|---|---|---|---|
| Combine ADMM-based phase retrieval with RED using a DnCNN denoiser | Fourier phase retrieval with random initialization · α=0, overall | Average PSNR: 52.45 -> 61.47 | Helped |
| Combine ADMM-based phase retrieval with RED using a DnCNN denoiser | Fourier phase retrieval with random initialization · α=4, overall | Average PSNR: 28.05 -> 36.06 | Helped |
| Use Deep-ITA-S instead of the strongest baseline, prDeep | Fourier phase retrieval initialized with HIO · α=8, overall | Average PSNR: 29.62 -> 33.04 | Helped |
| Use Deep-ITA-S instead of the strongest baseline, prDeep | Fourier phase retrieval initialized with HIO · α=12, overall | Average PSNR: 27.85 -> 31.17 | Helped |
| Use Deep-ITA-S instead of the strongest baseline, prDeep | Fourier phase retrieval initialized with HIO · α=16, overall | Average PSNR: 25.54 -> 27.76 | Helped |
| Relax the oversampling constraint rather than the Fourier measurement constraint | Deep-ITA-S versus Deep-ITA-F · Fourier phase retrieval, HIO initialization, α=12, overall | Average PSNR: 29.60 -> 31.17 | Helped |
Closest papers by meaning
- prDeep: Robust Phase Retrieval with a Flexible Deep Network (ICML 2018 · similarity 0.92)
- Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Imaging Inverse Problems (NeurIPS 2025 · similarity 0.86)
- A Fast and Provable Algorithm for Sparse Phase Retrieval (ICLR 2024 · similarity 0.86)
- DiffFPR: Diffusion Prior for Oversampled Fourier Phase Retrieval (ICML 2024 · similarity 0.86)
- Stochastic Deep Restoration Priors for Imaging Inverse Problems (ICML 2025 · similarity 0.86)
- Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems (NeurIPS 2024 · 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.