{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OOJSF6SHL4CDCJCZGIH6X7LYP5","short_pith_number":"pith:OOJSF6SH","schema_version":"1.0","canonical_sha256":"739322fa475f04312459320febfd787f471de2e72200722fd59a9ce6d6652981","source":{"kind":"arxiv","id":"2406.04629","version":1},"attestation_state":"computed","paper":{"title":"STAR: Skeleton-aware Text-based 4D Avatar Generation with In-Network Motion Retargeting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chen Tang, Mohan Kankanhalli, Yongkang Wong, Zenghao Chai","submitted_at":"2024-06-07T04:29:22Z","abstract_excerpt":"The creation of 4D avatars (i.e., animated 3D avatars) from text description typically uses text-to-image (T2I) diffusion models to synthesize 3D avatars in the canonical space and subsequently applies animation with target motions. However, such an optimization-by-animation paradigm has several drawbacks. (1) For pose-agnostic optimization, the rendered images in canonical pose for naive Score Distillation Sampling (SDS) exhibit domain gap and cannot preserve view-consistency using only T2I priors, and (2) For post hoc animation, simply applying the source motions to target 3D avatars yields "},"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":"2406.04629","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-07T04:29:22Z","cross_cats_sorted":["cs.GR","cs.MM"],"title_canon_sha256":"fa1ef607a9e034838915a68899509ae25509562bcc609b1f5d12603e7f1c72e3","abstract_canon_sha256":"a3486c9bc713cc30c838004942af72f4335e12252caaeef5e833e25f9ac5f008"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:46.651225Z","signature_b64":"r+ZZ+pGiqJAFBQVVWLQN5cAmbsaX53uFvyhJ/Zw+SAIhjjP5hYGsKqnLkCxYIDZb22R27ruo2crr7y3abubODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"739322fa475f04312459320febfd787f471de2e72200722fd59a9ce6d6652981","last_reissued_at":"2026-07-05T08:28:46.650759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:46.650759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STAR: Skeleton-aware Text-based 4D Avatar Generation with In-Network Motion Retargeting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chen Tang, Mohan Kankanhalli, Yongkang Wong, Zenghao Chai","submitted_at":"2024-06-07T04:29:22Z","abstract_excerpt":"The creation of 4D avatars (i.e., animated 3D avatars) from text description typically uses text-to-image (T2I) diffusion models to synthesize 3D avatars in the canonical space and subsequently applies animation with target motions. However, such an optimization-by-animation paradigm has several drawbacks. (1) For pose-agnostic optimization, the rendered images in canonical pose for naive Score Distillation Sampling (SDS) exhibit domain gap and cannot preserve view-consistency using only T2I priors, and (2) For post hoc animation, simply applying the source motions to target 3D avatars yields "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04629","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/2406.04629/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":"2406.04629","created_at":"2026-07-05T08:28:46.650816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04629v1","created_at":"2026-07-05T08:28:46.650816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04629","created_at":"2026-07-05T08:28:46.650816+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOJSF6SHL4CD","created_at":"2026-07-05T08:28:46.650816+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOJSF6SHL4CDCJCZ","created_at":"2026-07-05T08:28:46.650816+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOJSF6SH","created_at":"2026-07-05T08:28:46.650816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08189","citing_title":"AnyCharV: Bootstrap Controllable Character Video Generation with Fine-to-Coarse Guidance","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOJSF6SHL4CDCJCZGIH6X7LYP5","json":"https://pith.science/pith/OOJSF6SHL4CDCJCZGIH6X7LYP5.json","graph_json":"https://pith.science/api/pith-number/OOJSF6SHL4CDCJCZGIH6X7LYP5/graph.json","events_json":"https://pith.science/api/pith-number/OOJSF6SHL4CDCJCZGIH6X7LYP5/events.json","paper":"https://pith.science/paper/OOJSF6SH"},"agent_actions":{"view_html":"https://pith.science/pith/OOJSF6SHL4CDCJCZGIH6X7LYP5","download_json":"https://pith.science/pith/OOJSF6SHL4CDCJCZGIH6X7LYP5.json","view_paper":"https://pith.science/paper/OOJSF6SH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04629&json=true","fetch_graph":"https://pith.science/api/pith-number/OOJSF6SHL4CDCJCZGIH6X7LYP5/graph.json","fetch_events":"https://pith.science/api/pith-number/OOJSF6SHL4CDCJCZGIH6X7LYP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOJSF6SHL4CDCJCZGIH6X7LYP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOJSF6SHL4CDCJCZGIH6X7LYP5/action/storage_attestation","attest_author":"https://pith.science/pith/OOJSF6SHL4CDCJCZGIH6X7LYP5/action/author_attestation","sign_citation":"https://pith.science/pith/OOJSF6SHL4CDCJCZGIH6X7LYP5/action/citation_signature","submit_replication":"https://pith.science/pith/OOJSF6SHL4CDCJCZGIH6X7LYP5/action/replication_record"}},"created_at":"2026-07-05T08:28:46.650816+00:00","updated_at":"2026-07-05T08:28:46.650816+00:00"}