{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QUHFMISTW3YUXW5YOVCZVA4SEF","short_pith_number":"pith:QUHFMIST","schema_version":"1.0","canonical_sha256":"850e562253b6f14bdbb875459a83922154b744d0e22f80919a3a7ca22004f220","source":{"kind":"arxiv","id":"2506.18866","version":1},"attestation_state":"computed","paper":{"title":"OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jianke Zhu, Qijun Gan, Ruizi Yang, Shaofei Xue, Steven Hoi","submitted_at":"2025-06-23T17:33:03Z","abstract_excerpt":"Significant progress has been made in audio-driven human animation, while most existing methods focus mainly on facial movements, limiting their ability to create full-body animations with natural synchronization and fluidity. They also struggle with precise prompt control for fine-grained generation. To tackle these challenges, we introduce OmniAvatar, an innovative audio-driven full-body video generation model that enhances human animation with improved lip-sync accuracy and natural movements. OmniAvatar introduces a pixel-wise multi-hierarchical audio embedding strategy to better capture au"},"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":"2506.18866","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T17:33:03Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"3c8bbe4025f8f987215e10a850d882259b0ff9ac41ba7c2f13b04eb6cbfb4cfd","abstract_canon_sha256":"e8049b4f1cb91fe2bab47b929c558b07d2a772aff06402cc914c9c0fe8c5d025"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:57.225064Z","signature_b64":"3WEi5Z3wpBEI8FtH/WNufBkQ0DjGCXrfeXCcEvAVFWcIp2tGgDJpESEoezxkYRDSmojcf22X62cfNIRK3xICCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"850e562253b6f14bdbb875459a83922154b744d0e22f80919a3a7ca22004f220","last_reissued_at":"2026-07-05T11:25:57.224646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:57.224646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jianke Zhu, Qijun Gan, Ruizi Yang, Shaofei Xue, Steven Hoi","submitted_at":"2025-06-23T17:33:03Z","abstract_excerpt":"Significant progress has been made in audio-driven human animation, while most existing methods focus mainly on facial movements, limiting their ability to create full-body animations with natural synchronization and fluidity. They also struggle with precise prompt control for fine-grained generation. To tackle these challenges, we introduce OmniAvatar, an innovative audio-driven full-body video generation model that enhances human animation with improved lip-sync accuracy and natural movements. OmniAvatar introduces a pixel-wise multi-hierarchical audio embedding strategy to better capture au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18866","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/2506.18866/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":"2506.18866","created_at":"2026-07-05T11:25:57.224711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18866v1","created_at":"2026-07-05T11:25:57.224711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18866","created_at":"2026-07-05T11:25:57.224711+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUHFMISTW3YU","created_at":"2026-07-05T11:25:57.224711+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUHFMISTW3YUXW5Y","created_at":"2026-07-05T11:25:57.224711+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUHFMIST","created_at":"2026-07-05T11:25:57.224711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18326","citing_title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22905","citing_title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11180","citing_title":"Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01222","citing_title":"Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30849","citing_title":"SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22905","citing_title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25488","citing_title":"Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2511.04520","citing_title":"THEval. Evaluation Framework for Talking Head Video Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2512.04677","citing_title":"Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13669","citing_title":"EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27918","citing_title":"Generate Your Talking Avatar from Video Reference","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":234,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25819","citing_title":"Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":234,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23632","citing_title":"Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01809","citing_title":"TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02948","citing_title":"AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19636","citing_title":"CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11804","citing_title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10367","citing_title":"Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12856","citing_title":"PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordination","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09057","citing_title":"Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02948","citing_title":"AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18326","citing_title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QUHFMISTW3YUXW5YOVCZVA4SEF","json":"https://pith.science/pith/QUHFMISTW3YUXW5YOVCZVA4SEF.json","graph_json":"https://pith.science/api/pith-number/QUHFMISTW3YUXW5YOVCZVA4SEF/graph.json","events_json":"https://pith.science/api/pith-number/QUHFMISTW3YUXW5YOVCZVA4SEF/events.json","paper":"https://pith.science/paper/QUHFMIST"},"agent_actions":{"view_html":"https://pith.science/pith/QUHFMISTW3YUXW5YOVCZVA4SEF","download_json":"https://pith.science/pith/QUHFMISTW3YUXW5YOVCZVA4SEF.json","view_paper":"https://pith.science/paper/QUHFMIST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18866&json=true","fetch_graph":"https://pith.science/api/pith-number/QUHFMISTW3YUXW5YOVCZVA4SEF/graph.json","fetch_events":"https://pith.science/api/pith-number/QUHFMISTW3YUXW5YOVCZVA4SEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUHFMISTW3YUXW5YOVCZVA4SEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUHFMISTW3YUXW5YOVCZVA4SEF/action/storage_attestation","attest_author":"https://pith.science/pith/QUHFMISTW3YUXW5YOVCZVA4SEF/action/author_attestation","sign_citation":"https://pith.science/pith/QUHFMISTW3YUXW5YOVCZVA4SEF/action/citation_signature","submit_replication":"https://pith.science/pith/QUHFMISTW3YUXW5YOVCZVA4SEF/action/replication_record"}},"created_at":"2026-07-05T11:25:57.224711+00:00","updated_at":"2026-07-05T11:25:57.224711+00:00"}