{"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/scenedreamer-unbounded-3d-scene-generation","title":"SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections","arxiv_id":"2302.01330","date":"2023-02-02","proceeding":null,"authors":["Zhaoxi Chen","Guangcong Wang","Ziwei Liu"],"abstract":"In this work, we present SceneDreamer, an unconditional generative model for unbounded 3D scenes, which synthesizes large-scale 3D landscapes from random noise. Our framework is learned from in-the-wild 2D image collections only, without any 3D annotations. At the core of SceneDreamer is a principled learning paradigm comprising 1) an efficient yet expressive 3D scene representation, 2) a generative scene parameterization, and 3) an effective renderer that can leverage the knowledge from 2D images. Our approach begins with an efficient bird's-eye-view (BEV) representation generated from simplex noise, which includes a height field for surface elevation and a semantic field for detailed scene semantics. This BEV scene representation enables 1) representing a 3D scene with quadratic complexity, 2) disentangled geometry and semantics, and 3) efficient training. Moreover, we propose a novel generative neural hash grid to parameterize the latent space based on 3D positions and scene semantics, aiming to encode generalizable features across various scenes. Lastly, a neural volumetric renderer, learned from 2D image collections through adversarial training, is employed to produce photorealistic images. Extensive experiments demonstrate the effectiveness of SceneDreamer and superiority over state-of-the-art methods in generating vivid yet diverse unbounded 3D worlds.","url_abs":"https://arxiv.org/abs/2302.01330v3","url_pdf":"https://arxiv.org/pdf/2302.01330v3.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":"scenedreamer-unbounded-3d-scene-generation","repo_url":"https://github.com/frozenburning/scenedreamer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"scene-generation","task_name":"Scene Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-generation-on-googleearth","task":"Scene Generation","dataset":"GoogleEarth","model":"SceneDreamer","rank_in_archive_order":3,"of":5,"metrics":{"Camera Error":"0.186","Depth Error":"0.152","FID":"213.56","KID":"0.216"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.01330","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}