{"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/structured-3d-latents-for-scalable-and","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","arxiv_id":"2412.01506","date":"2024-12-02","proceeding":"CVPR 2025 1","authors":["Jianfeng Xiang","Zelong Lv","Sicheng Xu","Yu Deng","Ruicheng Wang","BoWen Zhang","Dong Chen","Xin Tong","Jiaolong Yang"],"abstract":"We introduce a novel 3D generation method for versatile and high-quality 3D asset creation. The cornerstone is a unified Structured LATent (SLAT) representation which allows decoding to different output formats, such as Radiance Fields, 3D Gaussians, and meshes. This is achieved by integrating a sparsely-populated 3D grid with dense multiview visual features extracted from a powerful vision foundation model, comprehensively capturing both structural (geometry) and textural (appearance) information while maintaining flexibility during decoding. We employ rectified flow transformers tailored for SLAT as our 3D generation models and train models with up to 2 billion parameters on a large 3D asset dataset of 500K diverse objects. Our model generates high-quality results with text or image conditions, significantly surpassing existing methods, including recent ones at similar scales. We showcase flexible output format selection and local 3D editing capabilities which were not offered by previous models. Code, model, and data will be released.","url_abs":"https://arxiv.org/abs/2412.01506v2","url_pdf":"https://arxiv.org/pdf/2412.01506v2.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":"structured-3d-latents-for-scalable-and","repo_url":"https://github.com/Microsoft/TRELLIS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"structured-3d-latents-for-scalable-and","repo_url":"https://github.com/ryanhangzhou/bootplace","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-generation","task_name":"3D Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.01506","atlas_url":"https://app.syntology.ai/?focus=2412.01506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01506"}},"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/Microsoft/TRELLIS","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ryanhangzhou/bootplace","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"official":{"samples":10,"ran":4,"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":"ac0e42d6fbcfbbe6","entry":"l1_loss","repo":"Microsoft/TRELLIS","repo_kind":"official","path":"trellis/utils/loss_utils.py","file_url":"https://github.com/Microsoft/TRELLIS/blob/HEAD/trellis/utils/loss_utils.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":"ac0e42d6fbcfbbe6"}},{"code_sha256_prefix":"8c3b0f873ba11813","entry":"l2_loss","repo":"Microsoft/TRELLIS","repo_kind":"official","path":"trellis/utils/loss_utils.py","file_url":"https://github.com/Microsoft/TRELLIS/blob/HEAD/trellis/utils/loss_utils.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":"8c3b0f873ba11813"}},{"code_sha256_prefix":"03310bba324ae4fb","entry":"modulate","repo":"Microsoft/TRELLIS","repo_kind":"official","path":"trellis/modules/utils.py","file_url":"https://github.com/Microsoft/TRELLIS/blob/HEAD/trellis/modules/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03310bba324ae4fb"}},{"code_sha256_prefix":"129b804760b3115f","entry":"zero_module","repo":"Microsoft/TRELLIS","repo_kind":"official","path":"trellis/modules/utils.py","file_url":"https://github.com/Microsoft/TRELLIS/blob/HEAD/trellis/modules/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"129b804760b3115f"}},{"code_sha256_prefix":"6818f26f5c2a59a4","entry":"norm_layer","repo":"Microsoft/TRELLIS","repo_kind":"official","path":"trellis/models/sparse_structure_vae.py","file_url":"https://github.com/Microsoft/TRELLIS/blob/HEAD/trellis/models/sparse_structure_vae.py","link_basis":"first_harvest_node","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":"6818f26f5c2a59a4"}},{"code_sha256_prefix":"e6b8cd9f318cc00b","entry":"patchify","repo":"Microsoft/TRELLIS","repo_kind":"official","path":"trellis/modules/spatial.py","file_url":"https://github.com/Microsoft/TRELLIS/blob/HEAD/trellis/modules/spatial.py","link_basis":"first_harvest_node","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":"e6b8cd9f318cc00b"}},{"code_sha256_prefix":"9e5521078878a448","entry":"pixel_shuffle_3d","repo":"Microsoft/TRELLIS","repo_kind":"official","path":"trellis/modules/spatial.py","file_url":"https://github.com/Microsoft/TRELLIS/blob/HEAD/trellis/modules/spatial.py","link_basis":"first_harvest_node","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":"9e5521078878a448"}},{"code_sha256_prefix":"9136b5f9b735334b","entry":"scale_module","repo":"Microsoft/TRELLIS","repo_kind":"official","path":"trellis/modules/utils.py","file_url":"https://github.com/Microsoft/TRELLIS/blob/HEAD/trellis/modules/utils.py","link_basis":"first_harvest_node","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":"9136b5f9b735334b"}},{"code_sha256_prefix":"c6ce2d5852baecaa","entry":"smooth_l1_loss","repo":"Microsoft/TRELLIS","repo_kind":"official","path":"trellis/utils/loss_utils.py","file_url":"https://github.com/Microsoft/TRELLIS/blob/HEAD/trellis/utils/loss_utils.py","link_basis":"first_harvest_node","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":"c6ce2d5852baecaa"}},{"code_sha256_prefix":"d01c19a64a056d04","entry":"unpatchify","repo":"Microsoft/TRELLIS","repo_kind":"official","path":"trellis/modules/spatial.py","file_url":"https://github.com/Microsoft/TRELLIS/blob/HEAD/trellis/modules/spatial.py","link_basis":"first_harvest_node","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":"d01c19a64a056d04"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}