{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K266GKUGAB53ECYX6RVHLO34OJ","short_pith_number":"pith:K266GKUG","schema_version":"1.0","canonical_sha256":"56bde32a86007bb20b17f46a75bb7c7277e94ef29d7a953ca8d5563f02947327","source":{"kind":"arxiv","id":"2403.15612","version":2},"attestation_state":"computed","paper":{"title":"InterFusion: Text-Driven Generation of 3D Human-Object Interaction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyang Ma, Haibin Huang, Haowen Sun, Hui Huang, Kai Xu, Ruizhen Hu, Sisi Dai, Wenhao Li","submitted_at":"2024-03-22T20:49:26Z","abstract_excerpt":"In this study, we tackle the complex task of generating 3D human-object interactions (HOI) from textual descriptions in a zero-shot text-to-3D manner. We identify and address two key challenges: the unsatisfactory outcomes of direct text-to-3D methods in HOI, largely due to the lack of paired text-interaction data, and the inherent difficulties in simultaneously generating multiple concepts with complex spatial relationships. To effectively address these issues, we present InterFusion, a two-stage framework specifically designed for HOI generation. InterFusion involves human pose estimations d"},"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":"2403.15612","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T20:49:26Z","cross_cats_sorted":[],"title_canon_sha256":"41d5ee944f216bea806207229a561bf0b007b88702e4300bbb7c590014b10cf9","abstract_canon_sha256":"745db406708ae1acddb1aacf69ae14818f0a92095b16a833311a959724d7dcaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:36.872237Z","signature_b64":"V0+zWaQYh6yBskYR6n5t4kx+3NFdBaq2xf/CB3yQN+Tr+5dYZNVwTzSuiMS5AtcZz1CCIXTlfdMwmOP1XJ2lBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56bde32a86007bb20b17f46a75bb7c7277e94ef29d7a953ca8d5563f02947327","last_reissued_at":"2026-07-05T08:44:36.871827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:36.871827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InterFusion: Text-Driven Generation of 3D Human-Object Interaction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyang Ma, Haibin Huang, Haowen Sun, Hui Huang, Kai Xu, Ruizhen Hu, Sisi Dai, Wenhao Li","submitted_at":"2024-03-22T20:49:26Z","abstract_excerpt":"In this study, we tackle the complex task of generating 3D human-object interactions (HOI) from textual descriptions in a zero-shot text-to-3D manner. We identify and address two key challenges: the unsatisfactory outcomes of direct text-to-3D methods in HOI, largely due to the lack of paired text-interaction data, and the inherent difficulties in simultaneously generating multiple concepts with complex spatial relationships. To effectively address these issues, we present InterFusion, a two-stage framework specifically designed for HOI generation. InterFusion involves human pose estimations d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15612","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/2403.15612/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":"2403.15612","created_at":"2026-07-05T08:44:36.871883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15612v2","created_at":"2026-07-05T08:44:36.871883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15612","created_at":"2026-07-05T08:44:36.871883+00:00"},{"alias_kind":"pith_short_12","alias_value":"K266GKUGAB53","created_at":"2026-07-05T08:44:36.871883+00:00"},{"alias_kind":"pith_short_16","alias_value":"K266GKUGAB53ECYX","created_at":"2026-07-05T08:44:36.871883+00:00"},{"alias_kind":"pith_short_8","alias_value":"K266GKUG","created_at":"2026-07-05T08:44:36.871883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.24121","citing_title":"TextMesh4D: Zero-shot Text-to-4D Mesh Generation","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K266GKUGAB53ECYX6RVHLO34OJ","json":"https://pith.science/pith/K266GKUGAB53ECYX6RVHLO34OJ.json","graph_json":"https://pith.science/api/pith-number/K266GKUGAB53ECYX6RVHLO34OJ/graph.json","events_json":"https://pith.science/api/pith-number/K266GKUGAB53ECYX6RVHLO34OJ/events.json","paper":"https://pith.science/paper/K266GKUG"},"agent_actions":{"view_html":"https://pith.science/pith/K266GKUGAB53ECYX6RVHLO34OJ","download_json":"https://pith.science/pith/K266GKUGAB53ECYX6RVHLO34OJ.json","view_paper":"https://pith.science/paper/K266GKUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15612&json=true","fetch_graph":"https://pith.science/api/pith-number/K266GKUGAB53ECYX6RVHLO34OJ/graph.json","fetch_events":"https://pith.science/api/pith-number/K266GKUGAB53ECYX6RVHLO34OJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K266GKUGAB53ECYX6RVHLO34OJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K266GKUGAB53ECYX6RVHLO34OJ/action/storage_attestation","attest_author":"https://pith.science/pith/K266GKUGAB53ECYX6RVHLO34OJ/action/author_attestation","sign_citation":"https://pith.science/pith/K266GKUGAB53ECYX6RVHLO34OJ/action/citation_signature","submit_replication":"https://pith.science/pith/K266GKUGAB53ECYX6RVHLO34OJ/action/replication_record"}},"created_at":"2026-07-05T08:44:36.871883+00:00","updated_at":"2026-07-05T08:44:36.871883+00:00"}