{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/reproducing-ambientgan-generative-models-from","title":"Reproducing AmbientGAN: Generative models from lossy measurements","arxiv_id":"1810.10108","date":"2018-10-23","proceeding":null,"authors":["Mehdi Ahmadi","Timothy Nest","Mostafa Abdelnaim","Thanh-Dung Le"],"abstract":"In recent years, Generative Adversarial Networks (GANs) have shown\nsubstantial progress in modeling complex distributions of data. These networks\nhave received tremendous attention since they can generate implicit\nprobabilistic models that produce realistic data using a stochastic procedure.\nWhile such models have proven highly effective in diverse scenarios, they\nrequire a large set of fully-observed training samples. In many applications\naccess to such samples are difficult or even impractical and only noisy or\npartial observations of the desired distribution is available. Recent research\nhas tried to address the problem of incompletely observed samples to recover\nthe distribution of the data. \\citep{zhu2017unpaired} and\n\\citep{yeh2016semantic} proposed methods to solve ill-posed inverse problem\nusing cycle-consistency and latent-space mappings in adversarial networks,\nrespectively. \\citep{bora2017compressed} and \\citep{kabkab2018task} have\napplied similar adversarial approaches to the problem of compressed sensing. In\nthis work, we focus on a new variant of GAN models called AmbientGAN, which\nincorporates a measurement process (e.g. adding noise, data removal and\nprojection) into the GAN training. While in the standard GAN, the discriminator\ndistinguishes a generated image from a real image, in AmbientGAN model the\ndiscriminator has to separate a real measurement from a simulated measurement\nof a generated image. The results shown by \\citep{bora2018ambientgan} are quite\npromising for the problem of incomplete data, and have potentially important\nimplications for generative approaches to compressed sensing and ill-posed\nproblems.","url_abs":"http://arxiv.org/abs/1810.10108v1","url_pdf":"http://arxiv.org/pdf/1810.10108v1.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":"reproducing-ambientgan-generative-models-from","repo_url":"https://github.com/AshishBora/ambient-gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"compressed-sensing","task_name":"compressed sensing"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"AshishBora/ambient-gan","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"51637a6ce7f707ee85f6c458a5be1eb98d4fa5ea1359f6c8facd4785c9ec542d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}