{"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/3dn-3d-deformation-network","title":"3DN: 3D Deformation Network","arxiv_id":"1903.03322","date":"2019-03-08","proceeding":"CVPR 2019 6","authors":["Weiyue Wang","Duygu Ceylan","Radomir Mech","Ulrich Neumann"],"abstract":"Applications in virtual and augmented reality create a demand for rapid\ncreation and easy access to large sets of 3D models. An effective way to\naddress this demand is to edit or deform existing 3D models based on a\nreference, e.g., a 2D image which is very easy to acquire. Given such a source\n3D model and a target which can be a 2D image, 3D model, or a point cloud\nacquired as a depth scan, we introduce 3DN, an end-to-end network that deforms\nthe source model to resemble the target. Our method infers per-vertex offset\ndisplacements while keeping the mesh connectivity of the source model fixed. We\npresent a training strategy which uses a novel differentiable operation, mesh\nsampling operator, to generalize our method across source and target models\nwith varying mesh densities. Mesh sampling operator can be seamlessly\nintegrated into the network to handle meshes with different topologies.\nQualitative and quantitative results show that our method generates higher\nquality results compared to the state-of-the art learning-based methods for 3D\nshape generation. Code is available at github.com/laughtervv/3DN.","url_abs":"http://arxiv.org/abs/1903.03322v1","url_pdf":"http://arxiv.org/pdf/1903.03322v1.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":"3dn-3d-deformation-network","repo_url":"https://github.com/laughtervv/3DN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-shape-generation","task_name":"3D Shape Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.03322","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}