{"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/viewset-diffusion-0-image-conditioned-3d","title":"Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data","arxiv_id":"2306.07881","date":"2023-06-13","proceeding":"ICCV 2023 1","authors":["Stanislaw Szymanowicz","Christian Rupprecht","Andrea Vedaldi"],"abstract":"We present Viewset Diffusion, a diffusion-based generator that outputs 3D objects while only using multi-view 2D data for supervision. We note that there exists a one-to-one mapping between viewsets, i.e., collections of several 2D views of an object, and 3D models. Hence, we train a diffusion model to generate viewsets, but design the neural network generator to reconstruct internally corresponding 3D models, thus generating those too. We fit a diffusion model to a large number of viewsets for a given category of objects. The resulting generator can be conditioned on zero, one or more input views. Conditioned on a single view, it performs 3D reconstruction accounting for the ambiguity of the task and allowing to sample multiple solutions compatible with the input. The model performs reconstruction efficiently, in a feed-forward manner, and is trained using only rendering losses using as few as three views per viewset. Project page: szymanowiczs.github.io/viewset-diffusion.","url_abs":"https://arxiv.org/abs/2306.07881v2","url_pdf":"https://arxiv.org/pdf/2306.07881v2.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":"viewset-diffusion-0-image-conditioned-3d","repo_url":"https://github.com/szymanowiczs/viewset-diffusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"single-view-3d-reconstruction","task_name":"Single-View 3D Reconstruction"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.07881","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}