{"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/learning-a-hierarchical-latent-variable-model","title":"Learning a Hierarchical Latent-Variable Model of 3D Shapes","arxiv_id":"1705.05994","date":"2017-05-17","proceeding":null,"authors":["Shikun Liu","C. Lee Giles","Alexander G. Ororbia II"],"abstract":"We propose the Variational Shape Learner (VSL), a generative model that\nlearns the underlying structure of voxelized 3D shapes in an unsupervised\nfashion. Through the use of skip-connections, our model can successfully learn\nand infer a latent, hierarchical representation of objects. Furthermore,\nrealistic 3D objects can be easily generated by sampling the VSL's latent\nprobabilistic manifold. We show that our generative model can be trained\nend-to-end from 2D images to perform single image 3D model retrieval.\nExperiments show, both quantitatively and qualitatively, the improved\ngeneralization of our proposed model over a range of tasks, performing better\nor comparable to various state-of-the-art alternatives.","url_abs":"http://arxiv.org/abs/1705.05994v4","url_pdf":"http://arxiv.org/pdf/1705.05994v4.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":"learning-a-hierarchical-latent-variable-model","repo_url":"https://github.com/lorenmt/vsl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"3d-object-classification","task_name":"3D Object Classification"},{"task_slug":"3d-object-recognition","task_name":"3D Object Recognition"},{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"3d-shape-generation","task_name":"3D Shape Generation"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-recognition-on-modelnet40","task":"3D Object Recognition","dataset":"ModelNet40","model":"Variational Shape Learner","rank_in_archive_order":6,"of":6,"metrics":{"Accuracy":"84.5%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}