{"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/efficient-nonlinear-transforms-for-lossy","title":"Efficient Nonlinear Transforms for Lossy Image Compression","arxiv_id":"1802.00847","date":"2018-01-31","proceeding":null,"authors":["Johannes Ballé"],"abstract":"We assess the performance of two techniques in the context of nonlinear\ntransform coding with artificial neural networks, Sadam and GDN. Both\ntechniques have been successfully used in state-of-the-art image compression\nmethods, but their performance has not been individually assessed to this\npoint. Together, the techniques stabilize the training procedure of nonlinear\nimage transforms and increase their capacity to approximate the (unknown)\nrate-distortion optimal transform functions. Besides comparing their\nperformance to established alternatives, we detail the implementation of both\nmethods and provide open-source code along with the paper.","url_abs":"http://arxiv.org/abs/1802.00847v2","url_pdf":"http://arxiv.org/pdf/1802.00847v2.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":"efficient-nonlinear-transforms-for-lossy","repo_url":"https://github.com/tensorflow/compression","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"efficient-nonlinear-transforms-for-lossy","repo_url":"https://github.com/faymek/compression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"efficient-nonlinear-transforms-for-lossy","repo_url":"https://github.com/treammm/Compression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-compression","task_name":"Image Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.00847","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}