{"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/weakly-supervised-learning-of-indoor-geometry","title":"Weakly supervised learning of indoor geometry by dual warping","arxiv_id":"1808.03609","date":"2018-08-10","proceeding":null,"authors":["Pulak Purkait","Ujwal Bonde","Christopher Zach"],"abstract":"A major element of depth perception and 3D understanding is the ability to\npredict the 3D layout of a scene and its contained objects for a novel pose.\nIndoor environments are particularly suitable for novel view prediction, since\nthe set of objects in such environments is relatively restricted. In this work\nwe address the task of 3D prediction especially for indoor scenes by leveraging\nonly weak supervision. In the literature 3D scene prediction is usually solved\nvia a 3D voxel grid. However, such methods are limited to estimating rather\ncoarse 3D voxel grids, since predicting entire voxel spaces has large\ncomputational costs. Hence, our method operates in image-space rather than in\nvoxel space, and the task of 3D estimation essentially becomes a depth image\ncompletion problem. We propose a novel approach to easily generate training\ndata containing depth maps with realistic occlusions, and subsequently train a\nnetwork for completing those occluded regions. Using multiple publicly\navailable dataset~\\cite{song2017semantic,Silberman:ECCV12} we benchmark our\nmethod against existing approaches and are able to obtain superior performance.\nWe further demonstrate the flexibility of our method by presenting results for\nnew view synthesis of RGB-D images.","url_abs":"http://arxiv.org/abs/1808.03609v1","url_pdf":"http://arxiv.org/pdf/1808.03609v1.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":"weakly-supervised-learning-of-indoor-geometry","repo_url":"https://github.com/shurans/sscnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}