{"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/lossy-image-compression-with-compressive","title":"Lossy Image Compression with Compressive Autoencoders","arxiv_id":"1703.00395","date":"2017-03-01","proceeding":null,"authors":["Lucas Theis","Wenzhe Shi","Andrew Cunningham","Ferenc Huszár"],"abstract":"We propose a new approach to the problem of optimizing autoencoders for lossy\nimage compression. New media formats, changing hardware technology, as well as\ndiverse requirements and content types create a need for compression algorithms\nwhich are more flexible than existing codecs. Autoencoders have the potential\nto address this need, but are difficult to optimize directly due to the\ninherent non-differentiabilty of the compression loss. We here show that\nminimal changes to the loss are sufficient to train deep autoencoders\ncompetitive with JPEG 2000 and outperforming recently proposed approaches based\non RNNs. Our network is furthermore computationally efficient thanks to a\nsub-pixel architecture, which makes it suitable for high-resolution images.\nThis is in contrast to previous work on autoencoders for compression using\ncoarser approximations, shallower architectures, computationally expensive\nmethods, or focusing on small images.","url_abs":"http://arxiv.org/abs/1703.00395v1","url_pdf":"http://arxiv.org/pdf/1703.00395v1.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":"lossy-image-compression-with-compressive","repo_url":"https://github.com/FireFYF/SlimCAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"lossy-image-compression-with-compressive","repo_url":"https://github.com/FireFYF/modulatedautoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"lossy-image-compression-with-compressive","repo_url":"https://github.com/alexandru-dinu/cae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lossy-image-compression-with-compressive","repo_url":"https://github.com/pkorus/l3ic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-compression","task_name":"Image Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.00395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.00395"}},"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/FireFYF/modulatedautoencoder","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexandru-dinu/cae","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FireFYF/SlimCAE","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pkorus/l3ic","reach":{"status":"ok"}}],"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":0,"samples":[{"code_sha256_prefix":"31b60606aa087805","entry":"lin_interp","repo":"alexandru-dinu/cae","repo_kind":"listed","path":"src/smoothing.py","file_url":"https://github.com/alexandru-dinu/cae/blob/HEAD/src/smoothing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31b60606aa087805"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}