{"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/three-for-one-and-one-for-three-flow","title":"Three for one and one for three: Flow, Segmentation, and Surface Normals","arxiv_id":"1807.07473","date":"2018-07-19","proceeding":null,"authors":["Hoang-An Le","Anil S. Baslamisli","Thomas Mensink","Theo Gevers"],"abstract":"Optical flow, semantic segmentation, and surface normals represent different\ninformation modalities, yet together they bring better cues for scene\nunderstanding problems. In this paper, we study the influence between the three\nmodalities: how one impacts on the others and their efficiency in combination.\nWe employ a modular approach using a convolutional refinement network which is\ntrained supervised but isolated from RGB images to enforce joint modality\nfeatures. To assist the training process, we create a large-scale synthetic\noutdoor dataset that supports dense annotation of semantic segmentation,\noptical flow, and surface normals. The experimental results show positive\ninfluence among the three modalities, especially for objects' boundaries,\nregion consistency, and scene structures.","url_abs":"http://arxiv.org/abs/1807.07473v1","url_pdf":"http://arxiv.org/pdf/1807.07473v1.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":"three-for-one-and-one-for-three-flow","repo_url":"https://github.com/lhoangan/341n143","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"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}