{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/prdeep-robust-phase-retrieval-with-a-flexible","title":"prDeep: Robust Phase Retrieval with a Flexible Deep Network","arxiv_id":"1803.00212","date":"2018-03-01","proceeding":"ICML 2018 7","authors":["Christopher A. Metzler","Philip Schniter","Ashok Veeraraghavan","Richard G. Baraniuk"],"abstract":"Phase retrieval algorithms have become an important component in many modern\ncomputational imaging systems. For instance, in the context of ptychography and\nspeckle correlation imaging, they enable imaging past the diffraction limit and\nthrough scattering media, respectively. Unfortunately, traditional phase\nretrieval algorithms struggle in the presence of noise. Progress has been made\nrecently on more robust algorithms using signal priors, but at the expense of\nlimiting the range of supported measurement models (e.g., to Gaussian or coded\ndiffraction patterns). In this work we leverage the regularization-by-denoising\nframework and a convolutional neural network denoiser to create prDeep, a new\nphase retrieval algorithm that is both robust and broadly applicable. We test\nand validate prDeep in simulation to demonstrate that it is robust to noise and\ncan handle a variety of system models.\n  A MatConvNet implementation of prDeep is available at\nhttps://github.com/ricedsp/prDeep.","url_abs":"http://arxiv.org/abs/1803.00212v2","url_pdf":"http://arxiv.org/pdf/1803.00212v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"prdeep-robust-phase-retrieval-with-a-flexible","repo_url":"https://github.com/ricedsp/prDeep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"prdeep-robust-phase-retrieval-with-a-flexible","repo_url":"https://github.com/hekstra-lab/phase-retrieval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1803.00212","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}