{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NDV32FUK5PXTTPQ7HT6AJXXAYQ","short_pith_number":"pith:NDV32FUK","schema_version":"1.0","canonical_sha256":"68ebbd168aebef39be1f3cfc04dee0c41d78a3312f07e405085789057924e215","source":{"kind":"arxiv","id":"2403.02234","version":2},"attestation_state":"computed","paper":{"title":"3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Fangzhou Hong, Jiaxiang Tang, Liang Pan, Min Shi, Shuai Yang, Tengfei Wang, Tong Wu, Zhaoxi Chen, Ziang Cao, Ziwei Liu","submitted_at":"2024-03-04T17:26:28Z","abstract_excerpt":"We present a two-stage text-to-3D generation system, namely 3DTopia, which generates high-quality general 3D assets within 5 minutes using hybrid diffusion priors. The first stage samples from a 3D diffusion prior directly learned from 3D data. Specifically, it is powered by a text-conditioned tri-plane latent diffusion model, which quickly generates coarse 3D samples for fast prototyping. The second stage utilizes 2D diffusion priors to further refine the texture of coarse 3D models from the first stage. The refinement consists of both latent and pixel space optimization for high-quality text"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.02234","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-04T17:26:28Z","cross_cats_sorted":[],"title_canon_sha256":"62dc11a40be33143ccfa90473044c6f6ed2db6023f60b64bfb0fd701c9bf8996","abstract_canon_sha256":"78305d271f45bada6e9520592e3eeeacf158251f06d9e7889e9b5bbf2ff5f2aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:25.723843Z","signature_b64":"SHlzwXMXmz+dLWH2lCyox5cylASbU5ik/em2TMgOSRTgs8LdzBaErrrwLCH1WmOWXsuZh1cH2Rv4KNa5nO9OAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68ebbd168aebef39be1f3cfc04dee0c41d78a3312f07e405085789057924e215","last_reissued_at":"2026-07-05T08:16:25.723372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:25.723372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Fangzhou Hong, Jiaxiang Tang, Liang Pan, Min Shi, Shuai Yang, Tengfei Wang, Tong Wu, Zhaoxi Chen, Ziang Cao, Ziwei Liu","submitted_at":"2024-03-04T17:26:28Z","abstract_excerpt":"We present a two-stage text-to-3D generation system, namely 3DTopia, which generates high-quality general 3D assets within 5 minutes using hybrid diffusion priors. The first stage samples from a 3D diffusion prior directly learned from 3D data. Specifically, it is powered by a text-conditioned tri-plane latent diffusion model, which quickly generates coarse 3D samples for fast prototyping. The second stage utilizes 2D diffusion priors to further refine the texture of coarse 3D models from the first stage. The refinement consists of both latent and pixel space optimization for high-quality text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02234","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.02234/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2403.02234","created_at":"2026-07-05T08:16:25.723432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02234v2","created_at":"2026-07-05T08:16:25.723432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02234","created_at":"2026-07-05T08:16:25.723432+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDV32FUK5PXT","created_at":"2026-07-05T08:16:25.723432+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDV32FUK5PXTTPQ7","created_at":"2026-07-05T08:16:25.723432+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDV32FUK","created_at":"2026-07-05T08:16:25.723432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01803","citing_title":"PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21572","citing_title":"PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2502.06608","citing_title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01479","citing_title":"UniRecGen: Unifying Multi-View 3D Reconstruction and Generation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27504","citing_title":"REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05721","citing_title":"GaussianGrow: Geometry-aware Gaussian Growing from 3D Point Clouds with Text Guidance","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDV32FUK5PXTTPQ7HT6AJXXAYQ","json":"https://pith.science/pith/NDV32FUK5PXTTPQ7HT6AJXXAYQ.json","graph_json":"https://pith.science/api/pith-number/NDV32FUK5PXTTPQ7HT6AJXXAYQ/graph.json","events_json":"https://pith.science/api/pith-number/NDV32FUK5PXTTPQ7HT6AJXXAYQ/events.json","paper":"https://pith.science/paper/NDV32FUK"},"agent_actions":{"view_html":"https://pith.science/pith/NDV32FUK5PXTTPQ7HT6AJXXAYQ","download_json":"https://pith.science/pith/NDV32FUK5PXTTPQ7HT6AJXXAYQ.json","view_paper":"https://pith.science/paper/NDV32FUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02234&json=true","fetch_graph":"https://pith.science/api/pith-number/NDV32FUK5PXTTPQ7HT6AJXXAYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NDV32FUK5PXTTPQ7HT6AJXXAYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDV32FUK5PXTTPQ7HT6AJXXAYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDV32FUK5PXTTPQ7HT6AJXXAYQ/action/storage_attestation","attest_author":"https://pith.science/pith/NDV32FUK5PXTTPQ7HT6AJXXAYQ/action/author_attestation","sign_citation":"https://pith.science/pith/NDV32FUK5PXTTPQ7HT6AJXXAYQ/action/citation_signature","submit_replication":"https://pith.science/pith/NDV32FUK5PXTTPQ7HT6AJXXAYQ/action/replication_record"}},"created_at":"2026-07-05T08:16:25.723432+00:00","updated_at":"2026-07-05T08:16:25.723432+00:00"}