{"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/realpoint3d-point-cloud-generation-from-a","title":"RealPoint3D: Point Cloud Generation from a Single Image with Complex Background","arxiv_id":"1809.02743","date":"2018-09-08","proceeding":null,"authors":["Yan Xia","Yang Zhang","Dingfu Zhou","Xinyu Huang","Cheng Wang","Ruigang Yang"],"abstract":"3D point cloud generation by the deep neural network from a single image has\nbeen attracting more and more researchers' attention. However,\nrecently-proposed methods require the objects be captured with relatively clean\nbackgrounds, fixed viewpoint, while this highly limits its application in the\nreal environment. To overcome these drawbacks, we proposed to integrate the\nprior 3D shape knowledge into the network to guide the 3D generation. By taking\nadditional 3D information, the proposed network can handle the 3D object\ngeneration from a single real image captured from any viewpoint and complex\nbackground. Specifically, giving a query image, we retrieve the nearest shape\nmodel from a pre-prepared 3D model database. Then, the image together with the\nretrieved shape model is fed into the proposed network to generate the\nfine-grained 3D point cloud. The effectiveness of our proposed framework has\nbeen verified on different kinds of datasets. Experimental results show that\nthe proposed framework achieves state-of-the-art accuracy compared to other\nvolumetric-based and point set generation methods. Furthermore, the proposed\nframework works well for real images in complex backgrounds with various view\nangles.","url_abs":"http://arxiv.org/abs/1809.02743v1","url_pdf":"http://arxiv.org/pdf/1809.02743v1.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":"realpoint3d-point-cloud-generation-from-a","repo_url":"https://github.com/Yan-Xia/RealPoint3D","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"3d-generation","task_name":"3D Generation"},{"task_slug":"point-cloud-generation","task_name":"Point Cloud Generation"}],"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}