{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JALXR43FDRAHINKTTWA6FYVF45","short_pith_number":"pith:JALXR43F","schema_version":"1.0","canonical_sha256":"481778f3651c407435539d81e2e2a5e77e2b56f36fedef3329d8517af21a60ed","source":{"kind":"arxiv","id":"2503.16396","version":3},"attestation_state":"computed","paper":{"title":"SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Han Yao, Huaizu Jiang, Varun Jampani, Vikram Voleti, Yiming Xie","submitted_at":"2025-03-20T17:53:38Z","abstract_excerpt":"We present Stable Video 4D 2.0 (SV4D 2.0), a multi-view video diffusion model for dynamic 3D asset generation. Compared to its predecessor SV4D, SV4D 2.0 is more robust to occlusions and large motion, generalizes better to real-world videos, and produces higher-quality outputs in terms of detail sharpness and spatio-temporal consistency. We achieve this by introducing key improvements in multiple aspects: 1) network architecture: eliminating the dependency of reference multi-views and designing blending mechanism for 3D and frame attention, 2) data: enhancing quality and quantity of training d"},"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":"2503.16396","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T17:53:38Z","cross_cats_sorted":[],"title_canon_sha256":"2a8d89ae17474c7b1488cb189454ced411c42076009c4e3f37ca7b7086ddd1f7","abstract_canon_sha256":"f328013605b30c6f611aeff6af7e1ac89ee0c898b35256998287364a64b2fbba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:44.926853Z","signature_b64":"696cVfRuFZifTDFxu1eJ1UYR+FOrOjGev87Opp5sjFgW7olQGTkdOGwq6k/t3gq/Rj79AXERSeG8Uk/+6ElHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"481778f3651c407435539d81e2e2a5e77e2b56f36fedef3329d8517af21a60ed","last_reissued_at":"2026-07-05T10:38:44.926336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:44.926336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Han Yao, Huaizu Jiang, Varun Jampani, Vikram Voleti, Yiming Xie","submitted_at":"2025-03-20T17:53:38Z","abstract_excerpt":"We present Stable Video 4D 2.0 (SV4D 2.0), a multi-view video diffusion model for dynamic 3D asset generation. Compared to its predecessor SV4D, SV4D 2.0 is more robust to occlusions and large motion, generalizes better to real-world videos, and produces higher-quality outputs in terms of detail sharpness and spatio-temporal consistency. We achieve this by introducing key improvements in multiple aspects: 1) network architecture: eliminating the dependency of reference multi-views and designing blending mechanism for 3D and frame attention, 2) data: enhancing quality and quantity of training d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16396","kind":"arxiv","version":3},"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/2503.16396/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":"2503.16396","created_at":"2026-07-05T10:38:44.926395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16396v3","created_at":"2026-07-05T10:38:44.926395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16396","created_at":"2026-07-05T10:38:44.926395+00:00"},{"alias_kind":"pith_short_12","alias_value":"JALXR43FDRAH","created_at":"2026-07-05T10:38:44.926395+00:00"},{"alias_kind":"pith_short_16","alias_value":"JALXR43FDRAHINKT","created_at":"2026-07-05T10:38:44.926395+00:00"},{"alias_kind":"pith_short_8","alias_value":"JALXR43F","created_at":"2026-07-05T10:38:44.926395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00157","citing_title":"Progressive Pose-Guided 4D Animal Reconstruction from Monocular Video","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28215","citing_title":"HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02799","citing_title":"UNICA: A Unified Neural Framework for Controllable 3D Avatars","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04527","citing_title":"Velox: Learning Representations of 4D Geometry and Appearance","ref_index":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JALXR43FDRAHINKTTWA6FYVF45","json":"https://pith.science/pith/JALXR43FDRAHINKTTWA6FYVF45.json","graph_json":"https://pith.science/api/pith-number/JALXR43FDRAHINKTTWA6FYVF45/graph.json","events_json":"https://pith.science/api/pith-number/JALXR43FDRAHINKTTWA6FYVF45/events.json","paper":"https://pith.science/paper/JALXR43F"},"agent_actions":{"view_html":"https://pith.science/pith/JALXR43FDRAHINKTTWA6FYVF45","download_json":"https://pith.science/pith/JALXR43FDRAHINKTTWA6FYVF45.json","view_paper":"https://pith.science/paper/JALXR43F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16396&json=true","fetch_graph":"https://pith.science/api/pith-number/JALXR43FDRAHINKTTWA6FYVF45/graph.json","fetch_events":"https://pith.science/api/pith-number/JALXR43FDRAHINKTTWA6FYVF45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JALXR43FDRAHINKTTWA6FYVF45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JALXR43FDRAHINKTTWA6FYVF45/action/storage_attestation","attest_author":"https://pith.science/pith/JALXR43FDRAHINKTTWA6FYVF45/action/author_attestation","sign_citation":"https://pith.science/pith/JALXR43FDRAHINKTTWA6FYVF45/action/citation_signature","submit_replication":"https://pith.science/pith/JALXR43FDRAHINKTTWA6FYVF45/action/replication_record"}},"created_at":"2026-07-05T10:38:44.926395+00:00","updated_at":"2026-07-05T10:38:44.926395+00:00"}