{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/gaudi-a-neural-architect-for-immersive-3d","title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","arxiv_id":"2207.13751","date":"2022-07-27","proceeding":null,"authors":["Miguel Angel Bautista","Pengsheng Guo","Samira Abnar","Walter Talbott","Alexander Toshev","Zhuoyuan Chen","Laurent Dinh","Shuangfei Zhai","Hanlin Goh","Daniel Ulbricht","Afshin Dehghan","Josh Susskind"],"abstract":"We introduce GAUDI, a generative model capable of capturing the distribution of complex and realistic 3D scenes that can be rendered immersively from a moving camera. We tackle this challenging problem with a scalable yet powerful approach, where we first optimize a latent representation that disentangles radiance fields and camera poses. This latent representation is then used to learn a generative model that enables both unconditional and conditional generation of 3D scenes. Our model generalizes previous works that focus on single objects by removing the assumption that the camera pose distribution can be shared across samples. We show that GAUDI obtains state-of-the-art performance in the unconditional generative setting across multiple datasets and allows for conditional generation of 3D scenes given conditioning variables like sparse image observations or text that describes the scene.","url_abs":"https://arxiv.org/abs/2207.13751v1","url_pdf":"https://arxiv.org/pdf/2207.13751v1.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":"gaudi-a-neural-architect-for-immersive-3d","repo_url":"https://github.com/apple/ml-gaudi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"scene-generation","task_name":"Scene Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-arkitscenes","task":"Image Generation","dataset":"ARKitScenes","model":"GAUDI","rank_in_archive_order":1,"of":4,"metrics":{"FID":"37.35","FID (SwAV)":"4.14"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-arkitscenes","task":"Image Generation","dataset":"ARKitScenes","model":"GSN","rank_in_archive_order":2,"of":4,"metrics":{"FID":"79.54","FID (SwAV)":"10.21"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-arkitscenes","task":"Image Generation","dataset":"ARKitScenes","model":"GRAF","rank_in_archive_order":3,"of":4,"metrics":{"FID":"87.06","FID (SwAV)":"13.44"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-arkitscenes","task":"Image Generation","dataset":"ARKitScenes","model":"π-GAN","rank_in_archive_order":4,"of":4,"metrics":{"FID":"134.8","FID (SwAV)":"15.58"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-replica","task":"Image Generation","dataset":"Replica","model":"GAUDI","rank_in_archive_order":1,"of":4,"metrics":{"FID":"18.75","FID (SwAV)":"1.76"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-replica","task":"Image Generation","dataset":"Replica","model":"GSN","rank_in_archive_order":2,"of":4,"metrics":{"FID":"41.75","FID (SwAV)":"4.14"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-replica","task":"Image Generation","dataset":"Replica","model":"GRAF","rank_in_archive_order":3,"of":4,"metrics":{"FID":"65.37","FID (SwAV)":"5.76"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-replica","task":"Image Generation","dataset":"Replica","model":"π-GAN","rank_in_archive_order":4,"of":4,"metrics":{"FID":"166.55","FID (SwAV)":"13.17"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-vln-ce","task":"Image Generation","dataset":"VLN-CE","model":"GAUDI","rank_in_archive_order":1,"of":4,"metrics":{"FID":"18.52","FID (SwAV)":"3.63"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-vln-ce","task":"Image Generation","dataset":"VLN-CE","model":"GSN","rank_in_archive_order":2,"of":4,"metrics":{"FID":"43.32","FID (SwAV)":"6.19"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-vln-ce","task":"Image Generation","dataset":"VLN-CE","model":"GRAF","rank_in_archive_order":3,"of":4,"metrics":{"FID":"90.43","FID (SwAV)":"8.65"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-vln-ce","task":"Image Generation","dataset":"VLN-CE","model":"π-GAN","rank_in_archive_order":4,"of":4,"metrics":{"FID":"151.26","FID (SwAV)":"14.07"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-vizdoom","task":"Image Generation","dataset":"VizDoom","model":"GAUDI","rank_in_archive_order":1,"of":4,"metrics":{"FID":"33.7","FID (SwAV)":"3.24"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-vizdoom","task":"Image Generation","dataset":"VizDoom","model":"GSN","rank_in_archive_order":2,"of":4,"metrics":{"FID":"37.21","FID (SwAV)":"4.56"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-vizdoom","task":"Image Generation","dataset":"VizDoom","model":"GRAF","rank_in_archive_order":3,"of":4,"metrics":{"FID":"47.5","FID (SwAV)":"5.44"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-vizdoom","task":"Image Generation","dataset":"VizDoom","model":"π-GAN","rank_in_archive_order":4,"of":4,"metrics":{"FID":"143.55","FID (SwAV)":"15.26"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.13751","atlas_url":"https://app.syntology.ai/?focus=2207.13751","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2207.13751"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2207.13751\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2207.13751"},"call":"get_concepts_for_paper(arxiv_id=\"2207.13751\")"}],"by_repo":[{"repo":"apple/ml-gaudi","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5bc1397c22928e125dac7d07b3efb0a2b48ef2e0c3528c00db4de45a21b830d4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}