Research map / Learning theory and algorithms / Matrix and tensor methods
prDeep: Robust Phase Retrieval with a Flexible Deep Network
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 |
|---|---|---|---|
| Use prDeep instead of the strongest listed baseline | CDP phase retrieval · CDP α=9, natural images | PSNR: 39.9 -> 39.1 | Hurt |
| Use prDeep instead of the strongest listed baseline | CDP phase retrieval · CDP α=9, unnatural images | PSNR: 40.6 -> 40.1 | Hurt |
| Use prDeep instead of the strongest listed baseline | CDP phase retrieval · CDP α=27, natural images | PSNR: 32.6 -> 32.8 | Helped |
| Use prDeep instead of the strongest listed baseline | CDP phase retrieval · CDP α=27, unnatural images | PSNR: 33.4 -> 34.0 | Helped |
| Use prDeep instead of the strongest listed baseline | CDP phase retrieval · CDP α=81, natural images | PSNR: 24.5 -> 20.9 | Hurt |
| Use prDeep instead of the strongest listed baseline | CDP phase retrieval · CDP α=81, unnatural images | PSNR: 26.9 -> 24.5 | Hurt |
| Use prDeep instead of the strongest listed baseline | Fourier phase retrieval · Fourier α=2, natural images | PSNR: 29.3 -> 28.4 | Hurt |
| Use prDeep instead of the strongest listed baseline | Fourier phase retrieval · Fourier α=2, unnatural images | PSNR: 31.3 -> 30.6 | Hurt |
| Use prDeep instead of the strongest listed baseline | Fourier phase retrieval · Fourier α=3, natural images | PSNR: 26.0 -> 28.5 | Helped |
| Use prDeep instead of the strongest listed baseline | Fourier phase retrieval · Fourier α=3, unnatural images | PSNR: 25.8 -> 26.4 | Helped |
| Use prDeep instead of the strongest listed baseline | Fourier phase retrieval · Fourier α=4, natural images | PSNR: 22.0 -> 26.4 | Helped |
| Use prDeep instead of the strongest listed baseline | Fourier phase retrieval · Fourier α=4, unnatural images | PSNR: 23.4 -> 25.1 | Helped |
Closest papers by meaning
- When deep denoising meets iterative phase retrieval (ICML 2020 · similarity 0.92)
- Phase Retrieval Under a Generative Prior (NeurIPS 2018 · similarity 0.89)
- A Fast and Provable Algorithm for Sparse Phase Retrieval (ICLR 2024 · similarity 0.87)
- Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction (NeurIPS 2024 · similarity 0.85)
- Intrinsic Phase-Preserving Networks for Depth Super Resolution (AAAI 2024 · similarity 0.84)
- Unsupervised Deep Unrolling Networks for Phase Unwrapping (CVPR 2024 · similarity 0.84)
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.