{"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/quality-gated-convolutional-lstm-for","title":"Quality-Gated Convolutional LSTM for Enhancing Compressed Video","arxiv_id":"1903.04596","date":"2019-03-11","proceeding":null,"authors":["Ren Yang","Xiaoyan Sun","Mai Xu","Wen-Jun Zeng"],"abstract":"The past decade has witnessed great success in applying deep learning to\nenhance the quality of compressed video. However, the existing approaches aim\nat quality enhancement on a single frame, or only using fixed neighboring\nframes. Thus they fail to take full advantage of the inter-frame correlation in\nthe video. This paper proposes the Quality-Gated Convolutional Long Short-Term\nMemory (QG-ConvLSTM) network with bi-directional recurrent structure to fully\nexploit the advantageous information in a large range of frames. More\nimportantly, due to the obvious quality fluctuation among compressed frames,\nhigher quality frames can provide more useful information for other frames to\nenhance quality. Therefore, we propose learning the \"forget\" and \"input\" gates\nin the ConvLSTM cell from quality-related features. As such, the frames with\nvarious quality contribute to the memory in ConvLSTM with different importance,\nmaking the information of each frame reasonably and adequately used. Finally,\nthe experiments validate the effectiveness of our QG-ConvLSTM approach in\nadvancing the state-of-the-art quality enhancement of compressed video, and the\nablation study shows that our QG-ConvLSTM approach is learnt to make a\ntrade-off between quality and correlation when leveraging multi-frame\ninformation. The project page: https://github.com/ryangchn/QG-ConvLSTM.git.","url_abs":"http://arxiv.org/abs/1903.04596v3","url_pdf":"http://arxiv.org/pdf/1903.04596v3.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":"quality-gated-convolutional-lstm-for","repo_url":"https://github.com/ryangchn/QG-ConvLSTM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"convlstm","method_name":"ConvLSTM"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.04596","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}