{"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/video-waterdrop-removal-via-spatio-temporal","title":"Video Waterdrop Removal via Spatio-Temporal Fusion in Driving Scenes","arxiv_id":"2302.05916","date":"2023-02-12","proceeding":null,"authors":["Qiang Wen","Yue Wu","Qifeng Chen"],"abstract":"The waterdrops on windshields during driving can cause severe visual obstructions, which may lead to car accidents. Meanwhile, the waterdrops can also degrade the performance of a computer vision system in autonomous driving. To address these issues, we propose an attention-based framework that fuses the spatio-temporal representations from multiple frames to restore visual information occluded by waterdrops. Due to the lack of training data for video waterdrop removal, we propose a large-scale synthetic dataset with simulated waterdrops in complex driving scenes on rainy days. To improve the generality of our proposed method, we adopt a cross-modality training strategy that combines synthetic videos and real-world images. Extensive experiments show that our proposed method can generalize well and achieve the best waterdrop removal performance in complex real-world driving scenes.","url_abs":"https://arxiv.org/abs/2302.05916v3","url_pdf":"https://arxiv.org/pdf/2302.05916v3.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":"video-waterdrop-removal-via-spatio-temporal","repo_url":"https://github.com/csqiangwen/Video_Waterdrop_Removal_in_Driving_Scenes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"raindrop-removal","task_name":"Raindrop Removal"},{"task_slug":"video-deraining","task_name":"Video deraining"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-deraining-on-video-waterdrop-removal","task":"Video deraining","dataset":"Video Waterdrop Removal Dataset","model":"VWR","rank_in_archive_order":3,"of":5,"metrics":{"PSNR":"30.72","SSIM":"0.9726"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.05916","atlas_url":"https://app.syntology.ai/?focus=2302.05916","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}