{"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/3d-object-reconstruction-from-a-single-depth","title":"3D Object Reconstruction from a Single Depth View with Adversarial Learning","arxiv_id":"1708.07969","date":"2017-08-26","proceeding":null,"authors":["Bo Yang","Hongkai Wen","Sen Wang","Ronald Clark","Andrew Markham","Niki Trigoni"],"abstract":"In this paper, we propose a novel 3D-RecGAN approach, which reconstructs the\ncomplete 3D structure of a given object from a single arbitrary depth view\nusing generative adversarial networks. Unlike the existing work which typically\nrequires multiple views of the same object or class labels to recover the full\n3D geometry, the proposed 3D-RecGAN only takes the voxel grid representation of\na depth view of the object as input, and is able to generate the complete 3D\noccupancy grid by filling in the occluded/missing regions. The key idea is to\ncombine the generative capabilities of autoencoders and the conditional\nGenerative Adversarial Networks (GAN) framework, to infer accurate and\nfine-grained 3D structures of objects in high-dimensional voxel space.\nExtensive experiments on large synthetic datasets show that the proposed\n3D-RecGAN significantly outperforms the state of the art in single view 3D\nobject reconstruction, and is able to reconstruct unseen types of objects. Our\ncode and data are available at: https://github.com/Yang7879/3D-RecGAN.","url_abs":"http://arxiv.org/abs/1708.07969v1","url_pdf":"http://arxiv.org/pdf/1708.07969v1.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":"3d-object-reconstruction-from-a-single-depth","repo_url":"https://github.com/Yang7879/3D-RecGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"3d-object-reconstruction-from-a-single-depth","repo_url":"https://github.com/zxpzhong/3D-RecGAN-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-object-reconstruction","task_name":"3D Object Reconstruction"},{"task_slug":"3d-geometry","task_name":"3D geometry"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-reconstruction","task_name":"Object Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1708.07969","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}