{"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-residual-network-for-joint-demosaicing","title":"Deep Residual Network for Joint Demosaicing and Super-Resolution","arxiv_id":"1802.06573","date":"2018-02-19","proceeding":null,"authors":["Ruofan Zhou","Radhakrishna Achanta","Sabine Süsstrunk"],"abstract":"In digital photography, two image restoration tasks have been studied\nextensively and resolved independently: demosaicing and super-resolution. Both\nthese tasks are related to resolution limitations of the camera. Performing\nsuper-resolution on a demosaiced images simply exacerbates the artifacts\nintroduced by demosaicing. In this paper, we show that such accumulation of\nerrors can be easily averted by jointly performing demosaicing and\nsuper-resolution. To this end, we propose a deep residual network for learning\nan end-to-end mapping between Bayer images and high-resolution images. By\ntraining on high-quality samples, our deep residual demosaicing and\nsuper-resolution network is able to recover high-quality super-resolved images\nfrom low-resolution Bayer mosaics in a single step without producing the\nartifacts common to such processing when the two operations are done\nseparately. We perform extensive experiments to show that our deep residual\nnetwork achieves demosaiced and super-resolved images that are superior to the\nstate-of-the-art both qualitatively and in terms of PSNR and SSIM metrics.","url_abs":"http://arxiv.org/abs/1802.06573v1","url_pdf":"http://arxiv.org/pdf/1802.06573v1.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-residual-network-for-joint-demosaicing","repo_url":"https://github.com/zxr931120/-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"demosaicking","task_name":"Demosaicking"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"ssim","task_name":"SSIM"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.06573","atlas_url":"https://app.syntology.ai/?focus=1802.06573","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}