{"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-convolutional-autoencoder-based-lossy","title":"Deep Convolutional AutoEncoder-based Lossy Image Compression","arxiv_id":"1804.09535","date":"2018-04-25","proceeding":null,"authors":["Zhengxue Cheng","Heming Sun","Masaru Takeuchi","Jiro Katto"],"abstract":"Image compression has been investigated as a fundamental research topic for\nmany decades. Recently, deep learning has achieved great success in many\ncomputer vision tasks, and is gradually being used in image compression. In\nthis paper, we present a lossy image compression architecture, which utilizes\nthe advantages of convolutional autoencoder (CAE) to achieve a high coding\nefficiency. First, we design a novel CAE architecture to replace the\nconventional transforms and train this CAE using a rate-distortion loss\nfunction. Second, to generate a more energy-compact representation, we utilize\nthe principal components analysis (PCA) to rotate the feature maps produced by\nthe CAE, and then apply the quantization and entropy coder to generate the\ncodes. Experimental results demonstrate that our method outperforms traditional\nimage coding algorithms, by achieving a 13.7% BD-rate decrement on the Kodak\ndatabase images compared to JPEG2000. Besides, our method maintains a moderate\ncomplexity similar to JPEG2000.","url_abs":"http://arxiv.org/abs/1804.09535v1","url_pdf":"http://arxiv.org/pdf/1804.09535v1.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-convolutional-autoencoder-based-lossy","repo_url":"https://github.com/cachett/DCGANandCAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-compression","task_name":"Image Compression"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.09535","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}