{"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/cubes3d-neural-network-based-optical-flow-in","title":"Cubes3D: Neural Network based Optical Flow in Omnidirectional Image Scenes","arxiv_id":"1804.09004","date":"2018-04-24","proceeding":null,"authors":["André Apitzsch","Roman Seidel","Gangolf Hirtz"],"abstract":"Optical flow estimation with convolutional neural networks (CNNs) has\nrecently solved various tasks of computer vision successfully. In this paper we\nadapt a state-of-the-art approach for optical flow estimation to\nomnidirectional images. We investigate CNN architectures to determine high\nmotion variations caused by the geometry of fish-eye images. Further we\ndetermine the qualitative influence of texture on the non-rigid object to the\nmotion vectors. For evaluation of the results we create ground truth motion\nfields synthetically. The ground truth contains cubes with static background.\nWe test variations of pre-trained FlowNet 2.0 architectures by indicating\ncommon error metrics. We generate competitive results for the motion of the\nforeground with inhomogeneous texture on the moving object.","url_abs":"http://arxiv.org/abs/1804.09004v2","url_pdf":"http://arxiv.org/pdf/1804.09004v2.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":"cubes3d-neural-network-based-optical-flow-in","repo_url":"https://gitlab.com/auxilia/cubes3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}