{"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/xcube-mathcal-x-3-large-scale-3d-generative","title":"XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies","arxiv_id":"2312.03806","date":"2023-12-06","proceeding":"CVPR 2024 1","authors":["Xuanchi Ren","Jiahui Huang","Xiaohui Zeng","Ken Museth","Sanja Fidler","Francis Williams"],"abstract":"We present XCube (abbreviated as $\\mathcal{X}^3$), a novel generative model for high-resolution sparse 3D voxel grids with arbitrary attributes. Our model can generate millions of voxels with a finest effective resolution of up to $1024^3$ in a feed-forward fashion without time-consuming test-time optimization. To achieve this, we employ a hierarchical voxel latent diffusion model which generates progressively higher resolution grids in a coarse-to-fine manner using a custom framework built on the highly efficient VDB data structure. Apart from generating high-resolution objects, we demonstrate the effectiveness of XCube on large outdoor scenes at scales of 100m$\\times$100m with a voxel size as small as 10cm. We observe clear qualitative and quantitative improvements over past approaches. In addition to unconditional generation, we show that our model can be used to solve a variety of tasks such as user-guided editing, scene completion from a single scan, and text-to-3D. The source code and more results can be found at https://research.nvidia.com/labs/toronto-ai/xcube/.","url_abs":"https://arxiv.org/abs/2312.03806v2","url_pdf":"https://arxiv.org/pdf/2312.03806v2.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":"xcube-mathcal-x-3-large-scale-3d-generative","repo_url":"https://github.com/nv-tlabs/XCube","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-shape-generation","task_name":"3D Shape Generation"},{"task_slug":"scene-generation","task_name":"Scene Generation"},{"task_slug":"text-to-3d","task_name":"Text to 3D"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"latent-diffusion-model","method_name":"Latent Diffusion Model"},{"method_slug":"sparse-convolutions","method_name":"Sparse Convolutions"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.03806","atlas_url":"https://app.syntology.ai/?focus=2312.03806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03806"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nv-tlabs/XCube","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":4,"ran_honours":1},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"a8c8cbcae846a467","entry":"hparams_handler","repo":"nv-tlabs/XCube","repo_kind":"official","path":"xcube/modules/autoencoding/hparams.py","file_url":"https://github.com/nv-tlabs/XCube/blob/HEAD/xcube/modules/autoencoding/hparams.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a8c8cbcae846a467"}},{"code_sha256_prefix":"75fdfa33a25ec622","entry":"lambda_lr_wrapper","repo":"nv-tlabs/XCube","repo_kind":"official","path":"xcube/models/autoencoder.py","file_url":"https://github.com/nv-tlabs/XCube/blob/HEAD/xcube/models/autoencoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"75fdfa33a25ec622"}},{"code_sha256_prefix":"c30d1fb49a30deb8","entry":"lambda_lr_wrapper","repo":"nv-tlabs/XCube","repo_kind":"official","path":"xcube/models/base_model.py","file_url":"https://github.com/nv-tlabs/XCube/blob/HEAD/xcube/models/base_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c30d1fb49a30deb8"}},{"code_sha256_prefix":"494e1e8b63161cd8","entry":"lambda_lr_wrapper","repo":"nv-tlabs/XCube","repo_kind":"official","path":"xcube/models/diffusion.py","file_url":"https://github.com/nv-tlabs/XCube/blob/HEAD/xcube/models/diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"494e1e8b63161cd8"}},{"code_sha256_prefix":"863fc64cd51264f0","entry":"reparametrize","repo":"nv-tlabs/XCube","repo_kind":"official","path":"xcube/models/autoencoder.py","file_url":"https://github.com/nv-tlabs/XCube/blob/HEAD/xcube/models/autoencoder.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"863fc64cd51264f0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}