{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IJQQXKFM4X2BE6W2C4QVHLLXPG","short_pith_number":"pith:IJQQXKFM","schema_version":"1.0","canonical_sha256":"42610ba8ace5f4127ada172153ad777982b3c59ae8c8b92838d9cca49415e8c9","source":{"kind":"arxiv","id":"2412.04470","version":1},"attestation_state":"computed","paper":{"title":"Turbo3D: Ultra-fast Text-to-3D Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fujun Luan, Hanzhe Hu, Hao Tan, Kai Zhang, Sai Bi, Shubham Tulsiani, Tianwei Yin, Yiwei Hu, Zexiang Xu","submitted_at":"2024-12-05T18:59:56Z","abstract_excerpt":"We present Turbo3D, an ultra-fast text-to-3D system capable of generating high-quality Gaussian splatting assets in under one second. Turbo3D employs a rapid 4-step, 4-view diffusion generator and an efficient feed-forward Gaussian reconstructor, both operating in latent space. The 4-step, 4-view generator is a student model distilled through a novel Dual-Teacher approach, which encourages the student to learn view consistency from a multi-view teacher and photo-realism from a single-view teacher. By shifting the Gaussian reconstructor's inputs from pixel space to latent space, we eliminate th"},"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":"2412.04470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T18:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"35b4a767f389f857b623f6b207089c0c320fcf4a87b6d0de029a70bde373b46d","abstract_canon_sha256":"0fa579ffc0b77d6b038e14ff9b20881957a0b0f9066442006f0574824ad20258"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:04.265886Z","signature_b64":"1oGlCDpT6vD/6RKsIeQBdbpAEbTcBFiAl+yTDTcuJ3wDMOWtQdSLG68rtYstH4UrSIGwo7to9UfyY/NJJClmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42610ba8ace5f4127ada172153ad777982b3c59ae8c8b92838d9cca49415e8c9","last_reissued_at":"2026-07-05T09:45:04.265386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:04.265386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Turbo3D: Ultra-fast Text-to-3D Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fujun Luan, Hanzhe Hu, Hao Tan, Kai Zhang, Sai Bi, Shubham Tulsiani, Tianwei Yin, Yiwei Hu, Zexiang Xu","submitted_at":"2024-12-05T18:59:56Z","abstract_excerpt":"We present Turbo3D, an ultra-fast text-to-3D system capable of generating high-quality Gaussian splatting assets in under one second. Turbo3D employs a rapid 4-step, 4-view diffusion generator and an efficient feed-forward Gaussian reconstructor, both operating in latent space. The 4-step, 4-view generator is a student model distilled through a novel Dual-Teacher approach, which encourages the student to learn view consistency from a multi-view teacher and photo-realism from a single-view teacher. By shifting the Gaussian reconstructor's inputs from pixel space to latent space, we eliminate th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04470","kind":"arxiv","version":1},"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/2412.04470/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":"2412.04470","created_at":"2026-07-05T09:45:04.265446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04470v1","created_at":"2026-07-05T09:45:04.265446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04470","created_at":"2026-07-05T09:45:04.265446+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJQQXKFM4X2B","created_at":"2026-07-05T09:45:04.265446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJQQXKFM4X2BE6W2","created_at":"2026-07-05T09:45:04.265446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJQQXKFM","created_at":"2026-07-05T09:45:04.265446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.07435","citing_title":"DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02736","citing_title":"THOM: Generating Physically Plausible Hand-Object Meshes From Text","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJQQXKFM4X2BE6W2C4QVHLLXPG","json":"https://pith.science/pith/IJQQXKFM4X2BE6W2C4QVHLLXPG.json","graph_json":"https://pith.science/api/pith-number/IJQQXKFM4X2BE6W2C4QVHLLXPG/graph.json","events_json":"https://pith.science/api/pith-number/IJQQXKFM4X2BE6W2C4QVHLLXPG/events.json","paper":"https://pith.science/paper/IJQQXKFM"},"agent_actions":{"view_html":"https://pith.science/pith/IJQQXKFM4X2BE6W2C4QVHLLXPG","download_json":"https://pith.science/pith/IJQQXKFM4X2BE6W2C4QVHLLXPG.json","view_paper":"https://pith.science/paper/IJQQXKFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04470&json=true","fetch_graph":"https://pith.science/api/pith-number/IJQQXKFM4X2BE6W2C4QVHLLXPG/graph.json","fetch_events":"https://pith.science/api/pith-number/IJQQXKFM4X2BE6W2C4QVHLLXPG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJQQXKFM4X2BE6W2C4QVHLLXPG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJQQXKFM4X2BE6W2C4QVHLLXPG/action/storage_attestation","attest_author":"https://pith.science/pith/IJQQXKFM4X2BE6W2C4QVHLLXPG/action/author_attestation","sign_citation":"https://pith.science/pith/IJQQXKFM4X2BE6W2C4QVHLLXPG/action/citation_signature","submit_replication":"https://pith.science/pith/IJQQXKFM4X2BE6W2C4QVHLLXPG/action/replication_record"}},"created_at":"2026-07-05T09:45:04.265446+00:00","updated_at":"2026-07-05T09:45:04.265446+00:00"}