{"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/interponet-a-brain-inspired-neural-network","title":"InterpoNet, A brain inspired neural network for optical flow dense interpolation","arxiv_id":"1611.09803","date":"2016-11-29","proceeding":"CVPR 2017 7","authors":["Shay Zweig","Lior Wolf"],"abstract":"Sparse-to-dense interpolation for optical flow is a fundamental phase in the\npipeline of most of the leading optical flow estimation algorithms. The current\nstate-of-the-art method for interpolation, EpicFlow, is a local average method\nbased on an edge aware geodesic distance. We propose a new data-driven\nsparse-to-dense interpolation algorithm based on a fully convolutional network.\nWe draw inspiration from the filling-in process in the visual cortex and\nintroduce lateral dependencies between neurons and multi-layer supervision into\nour learning process. We also show the importance of the image contour to the\nlearning process. Our method is robust and outperforms EpicFlow on competitive\noptical flow benchmarks with several underlying matching algorithms. This leads\nto state-of-the-art performance on the Sintel and KITTI 2012 benchmarks.","url_abs":"http://arxiv.org/abs/1611.09803v3","url_pdf":"http://arxiv.org/pdf/1611.09803v3.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":"interponet-a-brain-inspired-neural-network","repo_url":"https://github.com/shayzweig/InterpoNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"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}