{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2KSQKR5GVKHBAYN32RKDAAYYRJ","short_pith_number":"pith:2KSQKR5G","schema_version":"1.0","canonical_sha256":"d2a50547a6aa8e1061bbd4543003188a5b606ad9a09f52e95f342425d0d1088b","source":{"kind":"arxiv","id":"2412.01506","version":3},"attestation_state":"computed","paper":{"title":"Structured 3D Latents for Scalable and Versatile 3D Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A structured latent that merges sparse 3D grids with dense multiview features supports high-quality generation of 3D assets in multiple output formats from text or image input.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Dong Chen, Jianfeng Xiang, Jiaolong Yang, Ruicheng Wang, Sicheng Xu, Xin Tong, Yu Deng, Zelong Lv","submitted_at":"2024-12-02T13:58:38Z","abstract_excerpt":"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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2412.01506","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T13:58:38Z","cross_cats_sorted":[],"title_canon_sha256":"443f06edc7fa6690c52d391606e40ad8d719a0f4504a7a26de7b2284a959bdea","abstract_canon_sha256":"96be00091563b2de602b346b0c76a70c54d96c9ef69bb79de500a8ce3b3b2b68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:47.486663Z","signature_b64":"H3TcVYNgx/UGsoyTprnnYD/3kLuAxB++1AXaYHj1gcOxUSTFpoGCxAvi5t5a0A2tzfF4yawwaYW6tmeaHPjmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2a50547a6aa8e1061bbd4543003188a5b606ad9a09f52e95f342425d0d1088b","last_reissued_at":"2026-05-17T23:38:47.485867Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:47.485867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured 3D Latents for Scalable and Versatile 3D Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A structured latent that merges sparse 3D grids with dense multiview features supports high-quality generation of 3D assets in multiple output formats from text or image input.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Dong Chen, Jianfeng Xiang, Jiaolong Yang, Ruicheng Wang, Sicheng Xu, Xin Tong, Yu Deng, Zelong Lv","submitted_at":"2024-12-02T13:58:38Z","abstract_excerpt":"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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our model generates high-quality results with text or image conditions, significantly surpassing existing methods, including recent ones at similar scales.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The integration of a sparsely-populated 3D grid with dense multiview visual features from a vision foundation model comprehensively captures both structural geometry and textural appearance information while maintaining decoding flexibility.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SLAT provides a unified 3D latent representation enabling versatile high-quality generation across multiple output formats from text or image inputs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A structured latent that merges sparse 3D grids with dense multiview features supports high-quality generation of 3D assets in multiple output formats from text or image input.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ba52f5368bf37445b0ea7ad2f8587a46f42b06282058f3f1780ddaca9cbd6231"},"source":{"id":"2412.01506","kind":"arxiv","version":3},"verdict":{"id":"6e031692-e933-4e9f-be68-994e503b3da1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T15:05:40.004428Z","strongest_claim":"Our model generates high-quality results with text or image conditions, significantly surpassing existing methods, including recent ones at similar scales.","one_line_summary":"SLAT provides a unified 3D latent representation enabling versatile high-quality generation across multiple output formats from text or image inputs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The integration of a sparsely-populated 3D grid with dense multiview visual features from a vision foundation model comprehensively captures both structural geometry and textural appearance information while maintaining decoding flexibility.","pith_extraction_headline":"A structured latent that merges sparse 3D grids with dense multiview features supports high-quality generation of 3D assets in multiple output formats from text or image input."},"references":{"count":117,"sample":[{"doi":"","year":2024,"title":"Gpt-4o system card. 2024. 6, 16","work_id":"31f4f27a-bda9-4fa5-9486-8dd8a76923d3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":2,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"doi":"","year":null,"title":"Build- ing normalizing flows with stochastic interpolants","work_id":"18c42973-7784-4a94-9eb5-a5c41d8ae522","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Improving image generation with better captions","work_id":"283b326a-614b-42d1-b67f-4040cddad7e5","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Demystifying mmd gans","work_id":"d3a22946-30b0-4329-896b-dff78f4495e1","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":117,"snapshot_sha256":"3f8bfa1c68f0548796791686cf0bdacb503eaa262650f2c63bde43a220401fbc","internal_anchors":6},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2fb8040140c7f52b28f5d73f2ea22f598eb5d2c2696eb6765c1ff4ef87346ac1"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.01506","created_at":"2026-05-17T23:38:47.486097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01506v3","created_at":"2026-05-17T23:38:47.486097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01506","created_at":"2026-05-17T23:38:47.486097+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KSQKR5GVKHB","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KSQKR5GVKHBAYN3","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KSQKR5G","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":36,"internal_anchor_count":36,"sample":[{"citing_arxiv_id":"2605.23888","citing_title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2501.12202","citing_title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","ref_index":100,"is_internal_anchor":true},{"citing_arxiv_id":"2504.10466","citing_title":"Art3D: Training-Free 3D Generation from Flat-Colored Illustration","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21572","citing_title":"PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2511.16766","citing_title":"SVG360: Editable Multiview Vector Graphics from a Single SVG","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2601.21798","citing_title":"CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2602.21141","citing_title":"SynthRender and IRIS: Open-Source Framework and Dataset for Bidirectional Sim-Real Transfer in Industrial Object Perception","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2603.27309","citing_title":"MeshTailor: Cutting Seams via Generative Mesh Traversal","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18743","citing_title":"WorldString: Actionable World Representation","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20872","citing_title":"CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21121","citing_title":"ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28134","citing_title":"MeshReGen: A Unified 3D Geometry Regeneration Framework","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18743","citing_title":"WorldString: Actionable World Representation","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16745","citing_title":"EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":91,"is_internal_anchor":true},{"citing_arxiv_id":"2506.15442","citing_title":"Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2512.07834","citing_title":"Voxify3D: Pixel Art Meets Volumetric Rendering","ref_index":103,"is_internal_anchor":true},{"citing_arxiv_id":"2601.09211","citing_title":"Affostruction: 3D Affordance Grounding with Generative Reconstruction","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2506.16504","citing_title":"Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2601.11194","citing_title":"ATATA: One Algorithm to Align Them All","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2603.11633","citing_title":"MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.01479","citing_title":"UniRecGen: Unifying Multi-View 3D Reconstruction and Generation","ref_index":94,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28134","citing_title":"MeshReGen: A Unified 3D Geometry Regeneration Framework","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27504","citing_title":"REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11808","citing_title":"Pair2Scene: Learning Local Object Relations for Procedural Scene Generation","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KSQKR5GVKHBAYN32RKDAAYYRJ","json":"https://pith.science/pith/2KSQKR5GVKHBAYN32RKDAAYYRJ.json","graph_json":"https://pith.science/api/pith-number/2KSQKR5GVKHBAYN32RKDAAYYRJ/graph.json","events_json":"https://pith.science/api/pith-number/2KSQKR5GVKHBAYN32RKDAAYYRJ/events.json","paper":"https://pith.science/paper/2KSQKR5G"},"agent_actions":{"view_html":"https://pith.science/pith/2KSQKR5GVKHBAYN32RKDAAYYRJ","download_json":"https://pith.science/pith/2KSQKR5GVKHBAYN32RKDAAYYRJ.json","view_paper":"https://pith.science/paper/2KSQKR5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01506&json=true","fetch_graph":"https://pith.science/api/pith-number/2KSQKR5GVKHBAYN32RKDAAYYRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/2KSQKR5GVKHBAYN32RKDAAYYRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KSQKR5GVKHBAYN32RKDAAYYRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KSQKR5GVKHBAYN32RKDAAYYRJ/action/storage_attestation","attest_author":"https://pith.science/pith/2KSQKR5GVKHBAYN32RKDAAYYRJ/action/author_attestation","sign_citation":"https://pith.science/pith/2KSQKR5GVKHBAYN32RKDAAYYRJ/action/citation_signature","submit_replication":"https://pith.science/pith/2KSQKR5GVKHBAYN32RKDAAYYRJ/action/replication_record"}},"created_at":"2026-05-17T23:38:47.486097+00:00","updated_at":"2026-05-17T23:38:47.486097+00:00"}