{"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/when-image-denoising-meets-high-level-vision","title":"When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach","arxiv_id":"1706.04284","date":"2017-06-14","proceeding":null,"authors":["Ding Liu","Bihan Wen","Xianming Liu","Zhangyang Wang","Thomas S. Huang"],"abstract":"Conventionally, image denoising and high-level vision tasks are handled\nseparately in computer vision. In this paper, we cope with the two jointly and\nexplore the mutual influence between them. First we propose a convolutional\nneural network for image denoising which achieves the state-of-the-art\nperformance. Second we propose a deep neural network solution that cascades two\nmodules for image denoising and various high-level tasks, respectively, and use\nthe joint loss for updating only the denoising network via back-propagation. We\ndemonstrate that on one hand, the proposed denoiser has the generality to\novercome the performance degradation of different high-level vision tasks. On\nthe other hand, with the guidance of high-level vision information, the\ndenoising network can generate more visually appealing results. To the best of\nour knowledge, this is the first work investigating the benefit of exploiting\nimage semantics simultaneously for image denoising and high-level vision tasks\nvia deep learning. The code is available online\nhttps://github.com/Ding-Liu/DeepDenoising.","url_abs":"http://arxiv.org/abs/1706.04284v3","url_pdf":"http://arxiv.org/pdf/1706.04284v3.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":"when-image-denoising-meets-high-level-vision","repo_url":"https://github.com/Ding-Liu/DeepDenoising","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"when-image-denoising-meets-high-level-vision","repo_url":"https://github.com/rgsl888/U-Finger-A-Fingerprint-Denosing-Network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-denoising","task_name":"Image Denoising"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1706.04284","atlas_url":"https://app.syntology.ai/?focus=1706.04284","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}