{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5FGZ75ICZRR4YOU4N6GBTY5WO4","short_pith_number":"pith:5FGZ75IC","schema_version":"1.0","canonical_sha256":"e94d9ff502cc63cc3a9c6f8c19e3b6773b5771843ee6f0acf3e53743e09b0c8d","source":{"kind":"arxiv","id":"2309.07920","version":2},"attestation_state":"computed","paper":{"title":"Large-Vocabulary 3D Diffusion Model with Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, Liang Pan, Tong Wu, Ziang Cao, Ziwei Liu","submitted_at":"2023-09-14T17:59:53Z","abstract_excerpt":"Creating diverse and high-quality 3D assets with an automatic generative model is highly desirable. Despite extensive efforts on 3D generation, most existing works focus on the generation of a single category or a few categories. In this paper, we introduce a diffusion-based feed-forward framework for synthesizing massive categories of real-world 3D objects with a single generative model. Notably, there are three major challenges for this large-vocabulary 3D generation: a) the need for expressive yet efficient 3D representation; b) large diversity in geometry and texture across categories; c) "},"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":"2309.07920","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-14T17:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"ac2379eacede97f4d6a814e32b97ed502ce31f6a08a4b38edaa3f38189286c9b","abstract_canon_sha256":"659bfae40cc646ae6d02acba2f6735da48f3e01af50aca6d1068d91f1d36db89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:59.237836Z","signature_b64":"2S1kZkdY6yBvHvIlSFHDyWf5aXjRJszZHqrfwkKgXrRSfQJAFXFY9yXuqW7bo3iXhL4k0qA8XQ2FRZfGK/MsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e94d9ff502cc63cc3a9c6f8c19e3b6773b5771843ee6f0acf3e53743e09b0c8d","last_reissued_at":"2026-07-05T06:50:59.237349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:59.237349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Vocabulary 3D Diffusion Model with Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, Liang Pan, Tong Wu, Ziang Cao, Ziwei Liu","submitted_at":"2023-09-14T17:59:53Z","abstract_excerpt":"Creating diverse and high-quality 3D assets with an automatic generative model is highly desirable. Despite extensive efforts on 3D generation, most existing works focus on the generation of a single category or a few categories. In this paper, we introduce a diffusion-based feed-forward framework for synthesizing massive categories of real-world 3D objects with a single generative model. Notably, there are three major challenges for this large-vocabulary 3D generation: a) the need for expressive yet efficient 3D representation; b) large diversity in geometry and texture across categories; c) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07920","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/2309.07920/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":"2309.07920","created_at":"2026-07-05T06:50:59.237410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07920v2","created_at":"2026-07-05T06:50:59.237410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07920","created_at":"2026-07-05T06:50:59.237410+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FGZ75ICZRR4","created_at":"2026-07-05T06:50:59.237410+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FGZ75ICZRR4YOU4","created_at":"2026-07-05T06:50:59.237410+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FGZ75IC","created_at":"2026-07-05T06:50:59.237410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.02316","citing_title":"ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation","ref_index":45,"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":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5FGZ75ICZRR4YOU4N6GBTY5WO4","json":"https://pith.science/pith/5FGZ75ICZRR4YOU4N6GBTY5WO4.json","graph_json":"https://pith.science/api/pith-number/5FGZ75ICZRR4YOU4N6GBTY5WO4/graph.json","events_json":"https://pith.science/api/pith-number/5FGZ75ICZRR4YOU4N6GBTY5WO4/events.json","paper":"https://pith.science/paper/5FGZ75IC"},"agent_actions":{"view_html":"https://pith.science/pith/5FGZ75ICZRR4YOU4N6GBTY5WO4","download_json":"https://pith.science/pith/5FGZ75ICZRR4YOU4N6GBTY5WO4.json","view_paper":"https://pith.science/paper/5FGZ75IC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07920&json=true","fetch_graph":"https://pith.science/api/pith-number/5FGZ75ICZRR4YOU4N6GBTY5WO4/graph.json","fetch_events":"https://pith.science/api/pith-number/5FGZ75ICZRR4YOU4N6GBTY5WO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FGZ75ICZRR4YOU4N6GBTY5WO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FGZ75ICZRR4YOU4N6GBTY5WO4/action/storage_attestation","attest_author":"https://pith.science/pith/5FGZ75ICZRR4YOU4N6GBTY5WO4/action/author_attestation","sign_citation":"https://pith.science/pith/5FGZ75ICZRR4YOU4N6GBTY5WO4/action/citation_signature","submit_replication":"https://pith.science/pith/5FGZ75ICZRR4YOU4N6GBTY5WO4/action/replication_record"}},"created_at":"2026-07-05T06:50:59.237410+00:00","updated_at":"2026-07-05T06:50:59.237410+00:00"}