{"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-predictable-and-generative-vector","title":"Learning a Predictable and Generative Vector Representation for Objects","arxiv_id":"1603.08637","date":"2016-03-29","proceeding":null,"authors":["Rohit Girdhar","David F. Fouhey","Mikel Rodriguez","Abhinav Gupta"],"abstract":"What is a good vector representation of an object? We believe that it should\nbe generative in 3D, in the sense that it can produce new 3D objects; as well\nas be predictable from 2D, in the sense that it can be perceived from 2D\nimages. We propose a novel architecture, called the TL-embedding network, to\nlearn an embedding space with these properties. The network consists of two\ncomponents: (a) an autoencoder that ensures the representation is generative;\nand (b) a convolutional network that ensures the representation is predictable.\nThis enables tackling a number of tasks including voxel prediction from 2D\nimages and 3D model retrieval. Extensive experimental analysis demonstrates the\nusefulness and versatility of this embedding.","url_abs":"http://arxiv.org/abs/1603.08637v2","url_pdf":"http://arxiv.org/pdf/1603.08637v2.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-predictable-and-generative-vector","repo_url":"https://github.com/JeremyFisher/deep_level_sets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-a-predictable-and-generative-vector","repo_url":"https://github.com/JeremyFisher/few_shot_3dr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.08637","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}