{"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/neuralfield-ldm-scene-generation-with","title":"NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models","arxiv_id":"2304.09787","date":"2023-04-19","proceeding":"CVPR 2023 1","authors":["Seung Wook Kim","Bradley Brown","Kangxue Yin","Karsten Kreis","Katja Schwarz","Daiqing Li","Robin Rombach","Antonio Torralba","Sanja Fidler"],"abstract":"Automatically generating high-quality real world 3D scenes is of enormous interest for applications such as virtual reality and robotics simulation. Towards this goal, we introduce NeuralField-LDM, a generative model capable of synthesizing complex 3D environments. We leverage Latent Diffusion Models that have been successfully utilized for efficient high-quality 2D content creation. We first train a scene auto-encoder to express a set of image and pose pairs as a neural field, represented as density and feature voxel grids that can be projected to produce novel views of the scene. To further compress this representation, we train a latent-autoencoder that maps the voxel grids to a set of latent representations. A hierarchical diffusion model is then fit to the latents to complete the scene generation pipeline. We achieve a substantial improvement over existing state-of-the-art scene generation models. Additionally, we show how NeuralField-LDM can be used for a variety of 3D content creation applications, including conditional scene generation, scene inpainting and scene style manipulation.","url_abs":"https://arxiv.org/abs/2304.09787v1","url_pdf":"https://arxiv.org/pdf/2304.09787v1.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":[],"tasks":[{"task_slug":"scene-generation","task_name":"Scene Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"pixel-prediction","method_name":"Inpainting"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.09787","atlas_url":"https://app.syntology.ai/?focus=2304.09787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09787"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/justinpinkney/stable-diffusion","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_violates":3,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"found_in_text":{"samples":9,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"082e51fd548d78b2","entry":"append_dims","repo":"justinpinkney/stable-diffusion","repo_kind":"found_in_text","path":"ldm/models/diffusion/sampling_util.py","file_url":"https://github.com/justinpinkney/stable-diffusion/blob/HEAD/ldm/models/diffusion/sampling_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"082e51fd548d78b2"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"justinpinkney/stable-diffusion","repo_kind":"found_in_text","path":"ldm/modules/attention.py","file_url":"https://github.com/justinpinkney/stable-diffusion/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"justinpinkney/stable-diffusion","repo_kind":"found_in_text","path":"ldm/models/diffusion/classifier.py","file_url":"https://github.com/justinpinkney/stable-diffusion/blob/HEAD/ldm/models/diffusion/classifier.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"justinpinkney/stable-diffusion","repo_kind":"found_in_text","path":"ldm/modules/attention.py","file_url":"https://github.com/justinpinkney/stable-diffusion/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"9898fe8b041f354c","entry":"norm_thresholding","repo":"justinpinkney/stable-diffusion","repo_kind":"found_in_text","path":"ldm/models/diffusion/sampling_util.py","file_url":"https://github.com/justinpinkney/stable-diffusion/blob/HEAD/ldm/models/diffusion/sampling_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9898fe8b041f354c"}},{"code_sha256_prefix":"d48d8354986e3b0e","entry":"uniform_on_device","repo":"justinpinkney/stable-diffusion","repo_kind":"found_in_text","path":"ldm/models/diffusion/ddpm.py","file_url":"https://github.com/justinpinkney/stable-diffusion/blob/HEAD/ldm/models/diffusion/ddpm.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d48d8354986e3b0e"}},{"code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"justinpinkney/stable-diffusion","repo_kind":"found_in_text","path":"ldm/modules/attention.py","file_url":"https://github.com/justinpinkney/stable-diffusion/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a299fe5ae09e407"}},{"code_sha256_prefix":"4533e43e06a12dc5","entry":"download_models","repo":"justinpinkney/stable-diffusion","repo_kind":"found_in_text","path":"notebook_helpers.py","file_url":"https://github.com/justinpinkney/stable-diffusion/blob/HEAD/notebook_helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4533e43e06a12dc5"}},{"code_sha256_prefix":"751b5f9955c2159e","entry":"renorm_thresholding","repo":"justinpinkney/stable-diffusion","repo_kind":"found_in_text","path":"ldm/models/diffusion/sampling_util.py","file_url":"https://github.com/justinpinkney/stable-diffusion/blob/HEAD/ldm/models/diffusion/sampling_util.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"751b5f9955c2159e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}