{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QK42KLT6EAT4PNXRBZURKH6WTF","short_pith_number":"pith:QK42KLT6","schema_version":"1.0","canonical_sha256":"82b9a52e7e2027c7b6f10e69151fd6995ff11f9053a1cb47c329420d910eb127","source":{"kind":"arxiv","id":"2408.10588","version":2},"attestation_state":"computed","paper":{"title":"DEGAS: Detailed Expressions on Full-Body Gaussian Avatars","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Bo Dong, Duotun Wang, Hengyu Meng, Kang Zhang, Qing-Yao Tian, Yao-Dong Yang, Yu Zhang, Zeyu Cai, Zeyu Wang, Zhijing Shao","submitted_at":"2024-08-20T06:52:03Z","abstract_excerpt":"Although neural rendering has made significant advances in creating lifelike, animatable full-body and head avatars, incorporating detailed expressions into full-body avatars remains largely unexplored. We present DEGAS, the first 3D Gaussian Splatting (3DGS)-based modeling method for full-body avatars with rich facial expressions. Trained on multiview videos of a given subject, our method learns a conditional variational autoencoder that takes both the body motion and facial expression as driving signals to generate Gaussian maps in the UV layout. To drive the facial expressions, instead of t"},"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":"2408.10588","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-20T06:52:03Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"cd0faf1aeaa8a25153da52ebc9730ef52cb9f6ce5f58b81ee5a9c6ccb7a2b677","abstract_canon_sha256":"f283eb7d280becdf77e39942589a47985bb54ca27aa3ef956c4ea58fa4d919de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:23.248685Z","signature_b64":"sqkRaT+kl15HAYkaoKPedkuytzWJiQ9fAPd3QC+aKjo0ATO2Vca+I9PEE31jEuJ4JLAKHL+ZUCuQAqTVfq0KBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82b9a52e7e2027c7b6f10e69151fd6995ff11f9053a1cb47c329420d910eb127","last_reissued_at":"2026-07-05T10:11:23.248167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:23.248167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEGAS: Detailed Expressions on Full-Body Gaussian Avatars","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Bo Dong, Duotun Wang, Hengyu Meng, Kang Zhang, Qing-Yao Tian, Yao-Dong Yang, Yu Zhang, Zeyu Cai, Zeyu Wang, Zhijing Shao","submitted_at":"2024-08-20T06:52:03Z","abstract_excerpt":"Although neural rendering has made significant advances in creating lifelike, animatable full-body and head avatars, incorporating detailed expressions into full-body avatars remains largely unexplored. We present DEGAS, the first 3D Gaussian Splatting (3DGS)-based modeling method for full-body avatars with rich facial expressions. Trained on multiview videos of a given subject, our method learns a conditional variational autoencoder that takes both the body motion and facial expression as driving signals to generate Gaussian maps in the UV layout. To drive the facial expressions, instead of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10588","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/2408.10588/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":"2408.10588","created_at":"2026-07-05T10:11:23.248225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10588v2","created_at":"2026-07-05T10:11:23.248225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10588","created_at":"2026-07-05T10:11:23.248225+00:00"},{"alias_kind":"pith_short_12","alias_value":"QK42KLT6EAT4","created_at":"2026-07-05T10:11:23.248225+00:00"},{"alias_kind":"pith_short_16","alias_value":"QK42KLT6EAT4PNXR","created_at":"2026-07-05T10:11:23.248225+00:00"},{"alias_kind":"pith_short_8","alias_value":"QK42KLT6","created_at":"2026-07-05T10:11:23.248225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.12909","citing_title":"Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPs","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QK42KLT6EAT4PNXRBZURKH6WTF","json":"https://pith.science/pith/QK42KLT6EAT4PNXRBZURKH6WTF.json","graph_json":"https://pith.science/api/pith-number/QK42KLT6EAT4PNXRBZURKH6WTF/graph.json","events_json":"https://pith.science/api/pith-number/QK42KLT6EAT4PNXRBZURKH6WTF/events.json","paper":"https://pith.science/paper/QK42KLT6"},"agent_actions":{"view_html":"https://pith.science/pith/QK42KLT6EAT4PNXRBZURKH6WTF","download_json":"https://pith.science/pith/QK42KLT6EAT4PNXRBZURKH6WTF.json","view_paper":"https://pith.science/paper/QK42KLT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10588&json=true","fetch_graph":"https://pith.science/api/pith-number/QK42KLT6EAT4PNXRBZURKH6WTF/graph.json","fetch_events":"https://pith.science/api/pith-number/QK42KLT6EAT4PNXRBZURKH6WTF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QK42KLT6EAT4PNXRBZURKH6WTF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QK42KLT6EAT4PNXRBZURKH6WTF/action/storage_attestation","attest_author":"https://pith.science/pith/QK42KLT6EAT4PNXRBZURKH6WTF/action/author_attestation","sign_citation":"https://pith.science/pith/QK42KLT6EAT4PNXRBZURKH6WTF/action/citation_signature","submit_replication":"https://pith.science/pith/QK42KLT6EAT4PNXRBZURKH6WTF/action/replication_record"}},"created_at":"2026-07-05T10:11:23.248225+00:00","updated_at":"2026-07-05T10:11:23.248225+00:00"}