{"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/accurate-and-efficient-video-de-fencing-using","title":"Accurate and efficient video de-fencing using convolutional neural networks and temporal information","arxiv_id":"1806.10781","date":"2018-06-28","proceeding":null,"authors":["Chen Du","Byeongkeun Kang","Zheng Xu","Ji Dai","Truong Nguyen"],"abstract":"De-fencing is to eliminate the captured fence on an image or a video,\nproviding a clear view of the scene. It has been applied for many purposes\nincluding assisting photographers and improving the performance of computer\nvision algorithms such as object detection and recognition. However, the\nstate-of-the-art de-fencing methods have limited performance caused by the\ndifficulty of fence segmentation and also suffer from the motion of the camera\nor objects. To overcome these problems, we propose a novel method consisting of\nsegmentation using convolutional neural networks and a fast/robust recovery\nalgorithm. The segmentation algorithm using convolutional neural network\nachieves significant improvement in the accuracy of fence segmentation. The\nrecovery algorithm using optical flow produces plausible de-fenced images and\nvideos. The proposed method is experimented on both our diverse and complex\ndataset and publicly available datasets. The experimental results demonstrate\nthat the proposed method achieves the state-of-the-art performance for both\nsegmentation and content recovery.","url_abs":"http://arxiv.org/abs/1806.10781v1","url_pdf":"http://arxiv.org/pdf/1806.10781v1.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":"accurate-and-efficient-video-de-fencing-using","repo_url":"https://github.com/chen-du/De-fencing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}