{"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-bi-dense-networks-for-image-super","title":"Deep Bi-Dense Networks for Image Super-Resolution","arxiv_id":"1810.04873","date":"2018-10-11","proceeding":null,"authors":["Yucheng Wang","Jialiang Shen","Jian Zhang"],"abstract":"This paper proposes Deep Bi-Dense Networks (DBDN) for single image\nsuper-resolution. Our approach extends previous intra-block dense connection\napproaches by including novel inter-block dense connections. In this way,\nfeature information propagates from a single dense block to all subsequent\nblocks, instead of to a single successor. To build a DBDN, we firstly construct\nintra-dense blocks, which extract and compress abundant local features via\ndensely connected convolutional layers and compression layers for further\nfeature learning. Then, we use an inter-block dense net to connect intra-dense\nblocks, which allow each intra-dense block propagates its own local features to\nall successors. Additionally, our bi-dense construction connects each block to\nthe output, alleviating the vanishing gradient problems in training. The\nevaluation of our proposed method on five benchmark datasets shows that our\nDBDN outperforms the state of the art in SISR with a moderate number of network\nparameters.","url_abs":"http://arxiv.org/abs/1810.04873v1","url_pdf":"http://arxiv.org/pdf/1810.04873v1.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-bi-dense-networks-for-image-super","repo_url":"https://github.com/JannaShen/DBDN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}