{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4NNRTRBKHDXI5SBR6Z3H6R4KFO","short_pith_number":"pith:4NNRTRBK","schema_version":"1.0","canonical_sha256":"e35b19c42a38ee8ec831f6767f478a2b9d87eea988f7cf01e284d8db8f2b0d43","source":{"kind":"arxiv","id":"2406.04322","version":2},"attestation_state":"computed","paper":{"title":"DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Kortylewski, Alan Yuille, Qihao Liu, Song Bai, Yi Zhang","submitted_at":"2024-06-06T17:58:15Z","abstract_excerpt":"We present DIRECT-3D, a diffusion-based 3D generative model for creating high-quality 3D assets (represented by Neural Radiance Fields) from text prompts. Unlike recent 3D generative models that rely on clean and well-aligned 3D data, limiting them to single or few-class generation, our model is directly trained on extensive noisy and unaligned `in-the-wild' 3D assets, mitigating the key challenge (i.e., data scarcity) in large-scale 3D generation. In particular, DIRECT-3D is a tri-plane diffusion model that integrates two innovations: 1) A novel learning framework where noisy data are filtere"},"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":"2406.04322","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:58:15Z","cross_cats_sorted":[],"title_canon_sha256":"27b8317b43513fb2f0918b1fdc2ac33f976774a87e0784ba95dfeafd8902fc46","abstract_canon_sha256":"53e65b8d09e52cae335562ffb1c0acc10d0be60995c1130929702ec137324cba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:42.659514Z","signature_b64":"a6nPHc28E4k2EQHoiaz1jmNMULQ31ThfWr8sBRgA6JM0gCwJwskRxqZvwClHbNyKtXuTtiPkx6QkXmCkoWJxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e35b19c42a38ee8ec831f6767f478a2b9d87eea988f7cf01e284d8db8f2b0d43","last_reissued_at":"2026-07-05T08:28:42.659066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:42.659066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Kortylewski, Alan Yuille, Qihao Liu, Song Bai, Yi Zhang","submitted_at":"2024-06-06T17:58:15Z","abstract_excerpt":"We present DIRECT-3D, a diffusion-based 3D generative model for creating high-quality 3D assets (represented by Neural Radiance Fields) from text prompts. Unlike recent 3D generative models that rely on clean and well-aligned 3D data, limiting them to single or few-class generation, our model is directly trained on extensive noisy and unaligned `in-the-wild' 3D assets, mitigating the key challenge (i.e., data scarcity) in large-scale 3D generation. In particular, DIRECT-3D is a tri-plane diffusion model that integrates two innovations: 1) A novel learning framework where noisy data are filtere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04322","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/2406.04322/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":"2406.04322","created_at":"2026-07-05T08:28:42.659124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04322v2","created_at":"2026-07-05T08:28:42.659124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04322","created_at":"2026-07-05T08:28:42.659124+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NNRTRBKHDXI","created_at":"2026-07-05T08:28:42.659124+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NNRTRBKHDXI5SBR","created_at":"2026-07-05T08:28:42.659124+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NNRTRBK","created_at":"2026-07-05T08:28:42.659124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NNRTRBKHDXI5SBR6Z3H6R4KFO","json":"https://pith.science/pith/4NNRTRBKHDXI5SBR6Z3H6R4KFO.json","graph_json":"https://pith.science/api/pith-number/4NNRTRBKHDXI5SBR6Z3H6R4KFO/graph.json","events_json":"https://pith.science/api/pith-number/4NNRTRBKHDXI5SBR6Z3H6R4KFO/events.json","paper":"https://pith.science/paper/4NNRTRBK"},"agent_actions":{"view_html":"https://pith.science/pith/4NNRTRBKHDXI5SBR6Z3H6R4KFO","download_json":"https://pith.science/pith/4NNRTRBKHDXI5SBR6Z3H6R4KFO.json","view_paper":"https://pith.science/paper/4NNRTRBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04322&json=true","fetch_graph":"https://pith.science/api/pith-number/4NNRTRBKHDXI5SBR6Z3H6R4KFO/graph.json","fetch_events":"https://pith.science/api/pith-number/4NNRTRBKHDXI5SBR6Z3H6R4KFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NNRTRBKHDXI5SBR6Z3H6R4KFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NNRTRBKHDXI5SBR6Z3H6R4KFO/action/storage_attestation","attest_author":"https://pith.science/pith/4NNRTRBKHDXI5SBR6Z3H6R4KFO/action/author_attestation","sign_citation":"https://pith.science/pith/4NNRTRBKHDXI5SBR6Z3H6R4KFO/action/citation_signature","submit_replication":"https://pith.science/pith/4NNRTRBKHDXI5SBR6Z3H6R4KFO/action/replication_record"}},"created_at":"2026-07-05T08:28:42.659124+00:00","updated_at":"2026-07-05T08:28:42.659124+00:00"}