{"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/deep-image-compression-via-end-to-end","title":"Deep Image Compression via End-to-End Learning","arxiv_id":"1806.01496","date":"2018-06-05","proceeding":null,"authors":["Haojie Liu","Tong Chen","Qiu Shen","Tao Yue","Zhan Ma"],"abstract":"We present a lossy image compression method based on deep convolutional\nneural networks (CNNs), which outperforms the existing BPG, WebP, JPEG2000 and\nJPEG as measured via multi-scale structural similarity (MS-SSIM), at the same\nbit rate. Currently, most of the CNNs based approaches train the network using\na L2 loss between the reconstructions and the ground-truths in the pixel\ndomain, which leads to over-smoothing results and visual quality degradation\nespecially at a very low bit rate. Therefore, we improve the subjective quality\nwith the combination of a perception loss and an adversarial loss additionally.\nTo achieve better rate-distortion optimization (RDO), we also introduce an\neasy-to-hard transfer learning when adding quantization error and rate\nconstraint. Finally, we evaluate our method on public Kodak and the Test\nDataset P/M released by the Computer Vision Lab of ETH Zurich, resulting in\naveraged 7.81% and 19.1% BD-rate reduction over BPG, respectively.","url_abs":"http://arxiv.org/abs/1806.01496v1","url_pdf":"http://arxiv.org/pdf/1806.01496v1.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":"deep-image-compression-via-end-to-end","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"},{"task_slug":"ms-ssim","task_name":"MS-SSIM"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"ssim","task_name":"SSIM"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.01496","atlas_url":"https://app.syntology.ai/?focus=1806.01496","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}