{"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/noise-generation-for-compression-algorithms","title":"Noise generation for compression algorithms","arxiv_id":"1803.09165","date":"2018-03-24","proceeding":null,"authors":["Renata Khasanova","Jan Wassenberg","Jyrki Alakuijala"],"abstract":"In various Computer Vision and Signal Processing applications, noise is\ntypically perceived as a drawback of the image capturing system that ought to\nbe removed. We, on the other hand, claim that image noise, just as texture, is\nimportant for visual perception and, therefore, critical for lossy compression\nalgorithms that tend to make decompressed images look less realistic by\nremoving small image details. In this paper we propose a physically and\nbiologically inspired technique that learns a noise model at the encoding step\nof the compression algorithm and then generates the appropriate amount of\nadditive noise at the decoding step. Our method can significantly increase the\nrealism of the decompressed image at the cost of few bytes of additional memory\nspace regardless of the original image size. The implementation of our method\nis open-sourced and available at https://github.com/google/pik.","url_abs":"http://arxiv.org/abs/1803.09165v1","url_pdf":"http://arxiv.org/pdf/1803.09165v1.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":"noise-generation-for-compression-algorithms","repo_url":"https://github.com/google/pik","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}