{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QOC27YZSQGVN73V4NOD42BL47P","short_pith_number":"pith:QOC27YZS","schema_version":"1.0","canonical_sha256":"8385afe33281aadfeebc6b87cd057cfbf752606179b951eb041664591066aedb","source":{"kind":"arxiv","id":"2408.14732","version":2},"attestation_state":"computed","paper":{"title":"OctFusion: Octree-based Diffusion Models for 3D Shape Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Bojun Xiong, Peng-Shuai Wang, Si-Tong Wei, Xin-Yang Zheng, Yan-Pei Cao, Zhouhui Lian","submitted_at":"2024-08-27T01:55:40Z","abstract_excerpt":"Diffusion models have emerged as a popular method for 3D generation. However, it is still challenging for diffusion models to efficiently generate diverse and high-quality 3D shapes. In this paper, we introduce OctFusion, which can generate 3D shapes with arbitrary resolutions in 2.5 seconds on a single Nvidia 4090 GPU, and the extracted meshes are guaranteed to be continuous and manifold. The key components of OctFusion are the octree-based latent representation and the accompanying diffusion models. The representation combines the benefits of both implicit neural representations and explicit"},"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":"2408.14732","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T01:55:40Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"03c1dc81a813bd19f7c1a2d3b170c7012d325fa0e3b7018235b5913f6e969d54","abstract_canon_sha256":"13446fce71ba5447247d9d58782fee981260e4df0627606864035fdfc2be72eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:34.902881Z","signature_b64":"l+9ODEUuK1S9w8IV0cFmRwoExbaACaDoxT79m4Z+lKg+nTzDdNcKGH7cD+gIOuefVICyuUJePW5UEURks9mwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8385afe33281aadfeebc6b87cd057cfbf752606179b951eb041664591066aedb","last_reissued_at":"2026-07-05T11:17:34.902359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:34.902359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OctFusion: Octree-based Diffusion Models for 3D Shape Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Bojun Xiong, Peng-Shuai Wang, Si-Tong Wei, Xin-Yang Zheng, Yan-Pei Cao, Zhouhui Lian","submitted_at":"2024-08-27T01:55:40Z","abstract_excerpt":"Diffusion models have emerged as a popular method for 3D generation. However, it is still challenging for diffusion models to efficiently generate diverse and high-quality 3D shapes. In this paper, we introduce OctFusion, which can generate 3D shapes with arbitrary resolutions in 2.5 seconds on a single Nvidia 4090 GPU, and the extracted meshes are guaranteed to be continuous and manifold. The key components of OctFusion are the octree-based latent representation and the accompanying diffusion models. The representation combines the benefits of both implicit neural representations and explicit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14732","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/2408.14732/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":"2408.14732","created_at":"2026-07-05T11:17:34.902427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14732v2","created_at":"2026-07-05T11:17:34.902427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14732","created_at":"2026-07-05T11:17:34.902427+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOC27YZSQGVN","created_at":"2026-07-05T11:17:34.902427+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOC27YZSQGVN73V4","created_at":"2026-07-05T11:17:34.902427+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOC27YZS","created_at":"2026-07-05T11:17:34.902427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.01506","citing_title":"Structured 3D Latents for Scalable and Versatile 3D Generation","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOC27YZSQGVN73V4NOD42BL47P","json":"https://pith.science/pith/QOC27YZSQGVN73V4NOD42BL47P.json","graph_json":"https://pith.science/api/pith-number/QOC27YZSQGVN73V4NOD42BL47P/graph.json","events_json":"https://pith.science/api/pith-number/QOC27YZSQGVN73V4NOD42BL47P/events.json","paper":"https://pith.science/paper/QOC27YZS"},"agent_actions":{"view_html":"https://pith.science/pith/QOC27YZSQGVN73V4NOD42BL47P","download_json":"https://pith.science/pith/QOC27YZSQGVN73V4NOD42BL47P.json","view_paper":"https://pith.science/paper/QOC27YZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14732&json=true","fetch_graph":"https://pith.science/api/pith-number/QOC27YZSQGVN73V4NOD42BL47P/graph.json","fetch_events":"https://pith.science/api/pith-number/QOC27YZSQGVN73V4NOD42BL47P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOC27YZSQGVN73V4NOD42BL47P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOC27YZSQGVN73V4NOD42BL47P/action/storage_attestation","attest_author":"https://pith.science/pith/QOC27YZSQGVN73V4NOD42BL47P/action/author_attestation","sign_citation":"https://pith.science/pith/QOC27YZSQGVN73V4NOD42BL47P/action/citation_signature","submit_replication":"https://pith.science/pith/QOC27YZSQGVN73V4NOD42BL47P/action/replication_record"}},"created_at":"2026-07-05T11:17:34.902427+00:00","updated_at":"2026-07-05T11:17:34.902427+00:00"}