{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LWT5KWEGTTPUELAD4SSXK45EWB","short_pith_number":"pith:LWT5KWEG","schema_version":"1.0","canonical_sha256":"5da7d558869cdf422c03e4a57573a4b07d42b9dca9686f8ec172dc3d13b4a756","source":{"kind":"arxiv","id":"2605.13857","version":1},"attestation_state":"computed","paper":{"title":"MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MoZoo generates high-fidelity animal fur and muscle videos directly from coarse meshes using video diffusion.","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.GR","authors_text":"Bin Xia, Dongxia Liu, Jiancheng Zhang, Jie Ma, Jin Li, Jun Liang, Nisha Huang, Wenming Yang, Xiaochen Yang, Zhehan Kan","submitted_at":"2026-04-08T15:42:16Z","abstract_excerpt":"The creation of cinematic-quality animal effects necessitates the precise modeling of muscle and fur dynamics, a process that remains both labor-intensive and computationally expensive within traditional production workflows. While generative diffusion models have shown promise in diverse artistic workflows, their capacity for high-fidelity animal simulation remains largely unexploited. We present MoZoo, a generative dynamics solver that bypasses conventional refinement to synthesize high-fidelity animal videos from coarse meshes under multimodal guidance. We propose Role-Aware RoPE (RAR-RoPE)"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13857","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-04-08T15:42:16Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"0071f59056260dd9dfa6f732359bc6d8097682bce19ac7851573542594c19b9b","abstract_canon_sha256":"61b3da92e2803c5707d82aecbb4c408ff4c5e9a8e356cb8c4f8ae44c90aab115"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:19.535208Z","signature_b64":"00hlHZGck0XoiBDUufk+2aQNJgsZptkXaXIW0+JpSsb/CxO34ZlFYAoPCOEGAAeF45FZGyMzpiyvoEqVjRiCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5da7d558869cdf422c03e4a57573a4b07d42b9dca9686f8ec172dc3d13b4a756","last_reissued_at":"2026-05-17T23:39:19.534537Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:19.534537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MoZoo generates high-fidelity animal fur and muscle videos directly from coarse meshes using video diffusion.","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.GR","authors_text":"Bin Xia, Dongxia Liu, Jiancheng Zhang, Jie Ma, Jin Li, Jun Liang, Nisha Huang, Wenming Yang, Xiaochen Yang, Zhehan Kan","submitted_at":"2026-04-08T15:42:16Z","abstract_excerpt":"The creation of cinematic-quality animal effects necessitates the precise modeling of muscle and fur dynamics, a process that remains both labor-intensive and computationally expensive within traditional production workflows. While generative diffusion models have shown promise in diverse artistic workflows, their capacity for high-fidelity animal simulation remains largely unexploited. We present MoZoo, a generative dynamics solver that bypasses conventional refinement to synthesize high-fidelity animal videos from coarse meshes under multimodal guidance. We propose Role-Aware RoPE (RAR-RoPE)"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results demonstrate that MoZoo achieves high-fidelity fur simulation across diverse animal skeletons and layouts, preserving superior temporal and structural consistency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The synthetic-to-real pipeline used to create MoZoo-Data produces training examples whose distribution is close enough to real animal videos that the model generalizes without large domain gaps or artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MoZoo generates high-fidelity animal videos with fur and muscle dynamics from coarse meshes by extending video diffusion with role-aware RoPE and asymmetric decoupled attention, trained on a new synthetic-to-real dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MoZoo generates high-fidelity animal fur and muscle videos directly from coarse meshes using video diffusion.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"60990f82014449c282c1ea1f6d71465eefb2283bb41ed43c507edddccc0225dc"},"source":{"id":"2605.13857","kind":"arxiv","version":1},"verdict":{"id":"f5e7493b-1e16-40ff-8930-adbb72c7a3e4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T06:49:34.272646Z","strongest_claim":"Experimental results demonstrate that MoZoo achieves high-fidelity fur simulation across diverse animal skeletons and layouts, preserving superior temporal and structural consistency.","one_line_summary":"MoZoo generates high-fidelity animal videos with fur and muscle dynamics from coarse meshes by extending video diffusion with role-aware RoPE and asymmetric decoupled attention, trained on a new synthetic-to-real dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The synthetic-to-real pipeline used to create MoZoo-Data produces training examples whose distribution is close enough to real animal videos that the model generalizes without large domain gaps or artifacts.","pith_extraction_headline":"MoZoo generates high-fidelity animal fur and muscle videos directly from coarse meshes using video diffusion."},"references":{"count":56,"sample":[{"doi":"","year":2025,"title":"SAM 3: Segment Anything with Concepts","work_id":"4a72a006-2592-4554-aad0-a9c41a9f952d","ref_index":1,"cited_arxiv_id":"2511.16719","is_internal_anchor":true},{"doi":"","year":2026,"title":"Chang, D., Hou, J., Bozic, A., Neuberger, A., Juefei-Xu, F., Maury, O., Lin, G.W.C., Stuyck, T., Roble, D., Soleymani, M., Grabli, S.: Hairweaver: Few-shot photorealistic hair motion synthesis with si","work_id":"8c4c6b74-ef44-4e4f-963d-cc68d9559c19","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Chen, H., Zhang, Y., Cun, X., Xia, M., Wang, X., Weng, C., Shan, Y.: Videocrafter2: Overcoming data limitations for high-quality video diffusion models (2024)","work_id":"7d5d4096-1f40-4f57-a67a-ecf53da1f135","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/2775280.2792559","year":2015,"title":"ACM SIGGRAPH 2015 Talks , articleno =","work_id":"4110c632-8745-4200-8543-0afba4f998e3","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Diffusion Models Beat GANs on Image Synthesis","work_id":"2eb944bb-93ba-462c-8111-4e8c915dd873","ref_index":5,"cited_arxiv_id":"2105.05233","is_internal_anchor":true}],"resolved_work":56,"snapshot_sha256":"886980f020a499cfb71f503ea35630efec920265a516d0fd172a5b9e14ab5895","internal_anchors":17},"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":"2605.13857","created_at":"2026-05-17T23:39:19.534647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13857v1","created_at":"2026-05-17T23:39:19.534647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13857","created_at":"2026-05-17T23:39:19.534647+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWT5KWEGTTPU","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWT5KWEGTTPUELAD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWT5KWEG","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWT5KWEGTTPUELAD4SSXK45EWB","json":"https://pith.science/pith/LWT5KWEGTTPUELAD4SSXK45EWB.json","graph_json":"https://pith.science/api/pith-number/LWT5KWEGTTPUELAD4SSXK45EWB/graph.json","events_json":"https://pith.science/api/pith-number/LWT5KWEGTTPUELAD4SSXK45EWB/events.json","paper":"https://pith.science/paper/LWT5KWEG"},"agent_actions":{"view_html":"https://pith.science/pith/LWT5KWEGTTPUELAD4SSXK45EWB","download_json":"https://pith.science/pith/LWT5KWEGTTPUELAD4SSXK45EWB.json","view_paper":"https://pith.science/paper/LWT5KWEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13857&json=true","fetch_graph":"https://pith.science/api/pith-number/LWT5KWEGTTPUELAD4SSXK45EWB/graph.json","fetch_events":"https://pith.science/api/pith-number/LWT5KWEGTTPUELAD4SSXK45EWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWT5KWEGTTPUELAD4SSXK45EWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWT5KWEGTTPUELAD4SSXK45EWB/action/storage_attestation","attest_author":"https://pith.science/pith/LWT5KWEGTTPUELAD4SSXK45EWB/action/author_attestation","sign_citation":"https://pith.science/pith/LWT5KWEGTTPUELAD4SSXK45EWB/action/citation_signature","submit_replication":"https://pith.science/pith/LWT5KWEGTTPUELAD4SSXK45EWB/action/replication_record"}},"created_at":"2026-05-17T23:39:19.534647+00:00","updated_at":"2026-05-17T23:39:19.534647+00:00"}