{"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/deepvoxels-learning-persistent-3d-feature","title":"DeepVoxels: Learning Persistent 3D Feature Embeddings","arxiv_id":"1812.01024","date":"2018-12-03","proceeding":"CVPR 2019 6","authors":["Vincent Sitzmann","Justus Thies","Felix Heide","Matthias Nießner","Gordon Wetzstein","Michael Zollhöfer"],"abstract":"In this work, we address the lack of 3D understanding of generative neural\nnetworks by introducing a persistent 3D feature embedding for view synthesis.\nTo this end, we propose DeepVoxels, a learned representation that encodes the\nview-dependent appearance of a 3D scene without having to explicitly model its\ngeometry. At its core, our approach is based on a Cartesian 3D grid of\npersistent embedded features that learn to make use of the underlying 3D scene\nstructure. Our approach combines insights from 3D geometric computer vision\nwith recent advances in learning image-to-image mappings based on adversarial\nloss functions. DeepVoxels is supervised, without requiring a 3D reconstruction\nof the scene, using a 2D re-rendering loss and enforces perspective and\nmulti-view geometry in a principled manner. We apply our persistent 3D scene\nrepresentation to the problem of novel view synthesis demonstrating\nhigh-quality results for a variety of challenging scenes.","url_abs":"http://arxiv.org/abs/1812.01024v2","url_pdf":"http://arxiv.org/pdf/1812.01024v2.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":"deepvoxels-learning-persistent-3d-feature","repo_url":"https://github.com/vsitzmann/deepvoxels","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.01024","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}