{"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/image-reconstruction-by-domain-transform","title":"Image reconstruction by domain transform manifold learning","arxiv_id":"1704.08841","date":"2017-04-28","proceeding":null,"authors":["Bo Zhu","Jeremiah Z. Liu","Bruce R. Rosen","Matthew S. Rosen"],"abstract":"Image reconstruction plays a critical role in the implementation of all\ncontemporary imaging modalities across the physical and life sciences including\noptical, MRI, CT, PET, and radio astronomy. During an image acquisition, the\nsensor encodes an intermediate representation of an object in the sensor\ndomain, which is subsequently reconstructed into an image by an inversion of\nthe encoding function. Image reconstruction is challenging because analytic\nknowledge of the inverse transform may not exist a priori, especially in the\npresence of sensor non-idealities and noise. Thus, the standard reconstruction\napproach involves approximating the inverse function with multiple ad hoc\nstages in a signal processing chain whose composition depends on the details of\neach acquisition strategy, and often requires expert parameter tuning to\noptimize reconstruction performance. We present here a unified framework for\nimage reconstruction, AUtomated TransfOrm by Manifold APproximation (AUTOMAP),\nwhich recasts image reconstruction as a data-driven, supervised learning task\nthat allows a mapping between sensor and image domain to emerge from an\nappropriate corpus of training data. We implement AUTOMAP with a deep neural\nnetwork and exhibit its flexibility in learning reconstruction transforms for a\nvariety of MRI acquisition strategies, using the same network architecture and\nhyperparameters. We further demonstrate its efficiency in sparsely representing\ntransforms along low-dimensional manifolds, resulting in superior immunity to\nnoise and reconstruction artifacts compared with conventional handcrafted\nreconstruction methods. In addition to improving the reconstruction performance\nof existing acquisition methodologies, we anticipate accelerating the discovery\nof new acquisition strategies across modalities as the burden of reconstruction\nbecomes lifted by AUTOMAP and learned-reconstruction approaches.","url_abs":"http://arxiv.org/abs/1704.08841v1","url_pdf":"http://arxiv.org/pdf/1704.08841v1.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":"image-reconstruction-by-domain-transform","repo_url":"https://github.com/chongduan/MRI-AUTOMAP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"astronomy","task_name":"Astronomy"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.08841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.08841"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chongduan/MRI-AUTOMAP","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"1f7b96841e342679","entry":"create_x_motion","repo":"chongduan/MRI-AUTOMAP","repo_kind":"listed","path":"generate_input.py","file_url":"https://github.com/chongduan/MRI-AUTOMAP/blob/HEAD/generate_input.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1f7b96841e342679"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}