{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5TKUNZOB2TOSB46NCQR5L6EFZW","short_pith_number":"pith:5TKUNZOB","schema_version":"1.0","canonical_sha256":"ecd546e5c1d4dd20f3cd1423d5f885cd972672cda9c3ee522744683914f9db17","source":{"kind":"arxiv","id":"2409.08278","version":1},"attestation_state":"computed","paper":{"title":"DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ruining Li, Thomas Hanwen Zhu, Tomas Jakab","submitted_at":"2024-09-12T17:59:49Z","abstract_excerpt":"We present DreamHOI, a novel method for zero-shot synthesis of human-object interactions (HOIs), enabling a 3D human model to realistically interact with any given object based on a textual description. This task is complicated by the varying categories and geometries of real-world objects and the scarcity of datasets encompassing diverse HOIs. To circumvent the need for extensive data, we leverage text-to-image diffusion models trained on billions of image-caption pairs. We optimize the articulation of a skinned human mesh using Score Distillation Sampling (SDS) gradients obtained from these "},"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":"2409.08278","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-12T17:59:49Z","cross_cats_sorted":[],"title_canon_sha256":"ff0e475b2e6182cff310af01fb458af764d41709752f144c6a828f83f3b6aa3b","abstract_canon_sha256":"05d956043d0dd756145a9b0a7a7a1365528c35f331ec870f5058d386f14c9827"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:22.807762Z","signature_b64":"vUSguf0Qn1pgSz1IjKUBz3xt8YnjlI9NIdppbhJnxC+mXu7x57y6W4277Gp0emNFrCg+sNdBTv6rJbeqAYrCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecd546e5c1d4dd20f3cd1423d5f885cd972672cda9c3ee522744683914f9db17","last_reissued_at":"2026-07-05T09:06:22.807283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:22.807283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ruining Li, Thomas Hanwen Zhu, Tomas Jakab","submitted_at":"2024-09-12T17:59:49Z","abstract_excerpt":"We present DreamHOI, a novel method for zero-shot synthesis of human-object interactions (HOIs), enabling a 3D human model to realistically interact with any given object based on a textual description. This task is complicated by the varying categories and geometries of real-world objects and the scarcity of datasets encompassing diverse HOIs. To circumvent the need for extensive data, we leverage text-to-image diffusion models trained on billions of image-caption pairs. We optimize the articulation of a skinned human mesh using Score Distillation Sampling (SDS) gradients obtained from these "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08278","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/2409.08278/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":"2409.08278","created_at":"2026-07-05T09:06:22.807351+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08278v1","created_at":"2026-07-05T09:06:22.807351+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08278","created_at":"2026-07-05T09:06:22.807351+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TKUNZOB2TOS","created_at":"2026-07-05T09:06:22.807351+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TKUNZOB2TOSB46N","created_at":"2026-07-05T09:06:22.807351+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TKUNZOB","created_at":"2026-07-05T09:06:22.807351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02736","citing_title":"THOM: Generating Physically Plausible Hand-Object Meshes From Text","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5TKUNZOB2TOSB46NCQR5L6EFZW","json":"https://pith.science/pith/5TKUNZOB2TOSB46NCQR5L6EFZW.json","graph_json":"https://pith.science/api/pith-number/5TKUNZOB2TOSB46NCQR5L6EFZW/graph.json","events_json":"https://pith.science/api/pith-number/5TKUNZOB2TOSB46NCQR5L6EFZW/events.json","paper":"https://pith.science/paper/5TKUNZOB"},"agent_actions":{"view_html":"https://pith.science/pith/5TKUNZOB2TOSB46NCQR5L6EFZW","download_json":"https://pith.science/pith/5TKUNZOB2TOSB46NCQR5L6EFZW.json","view_paper":"https://pith.science/paper/5TKUNZOB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08278&json=true","fetch_graph":"https://pith.science/api/pith-number/5TKUNZOB2TOSB46NCQR5L6EFZW/graph.json","fetch_events":"https://pith.science/api/pith-number/5TKUNZOB2TOSB46NCQR5L6EFZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TKUNZOB2TOSB46NCQR5L6EFZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TKUNZOB2TOSB46NCQR5L6EFZW/action/storage_attestation","attest_author":"https://pith.science/pith/5TKUNZOB2TOSB46NCQR5L6EFZW/action/author_attestation","sign_citation":"https://pith.science/pith/5TKUNZOB2TOSB46NCQR5L6EFZW/action/citation_signature","submit_replication":"https://pith.science/pith/5TKUNZOB2TOSB46NCQR5L6EFZW/action/replication_record"}},"created_at":"2026-07-05T09:06:22.807351+00:00","updated_at":"2026-07-05T09:06:22.807351+00:00"}