{"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/crrn-multi-scale-guided-concurrent-reflection","title":"CRRN: Multi-Scale Guided Concurrent Reflection Removal Network","arxiv_id":"1805.11802","date":"2018-05-30","proceeding":"CVPR 2018 6","authors":["Renjie Wan","Boxin Shi","Ling-Yu Duan","Ah-Hwee Tan","Alex C. Kot"],"abstract":"Removing the undesired reflections from images taken through the glass is of\nbroad application to various computer vision tasks. Non-learning based methods\nutilize different handcrafted priors such as the separable sparse gradients\ncaused by different levels of blurs, which often fail due to their limited\ndescription capability to the properties of real-world reflections. In this\npaper, we propose the Concurrent Reflection Removal Network (CRRN) to tackle\nthis problem in a unified framework. Our proposed network integrates image\nappearance information and multi-scale gradient information with human\nperception inspired loss function, and is trained on a new dataset with 3250\nreflection images taken under diverse real-world scenes. Extensive experiments\non a public benchmark dataset show that the proposed method performs favorably\nagainst state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1805.11802v1","url_pdf":"http://arxiv.org/pdf/1805.11802v1.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":"crrn-multi-scale-guided-concurrent-reflection","repo_url":"https://github.com/He-jerry/CRRN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"reflection-removal","task_name":"Reflection Removal"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.11802","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}