{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7PJRVFJX7IVDUPCWY7F3EEUXWD","short_pith_number":"pith:7PJRVFJX","schema_version":"1.0","canonical_sha256":"fbd31a9537fa2a3a3c56c7cbb21297b0f05f4ca14e6694689277c91c7df0e1da","source":{"kind":"arxiv","id":"2311.02848","version":1},"attestation_state":"computed","paper":{"title":"Consistent4D: Consistent 360{\\deg} Dynamic Object Generation from Monocular Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jin Gao, Li Zhang, Weimin Hu, Yanqin Jiang, Yao Yao","submitted_at":"2023-11-06T03:26:43Z","abstract_excerpt":"In this paper, we present Consistent4D, a novel approach for generating 4D dynamic objects from uncalibrated monocular videos. Uniquely, we cast the 360-degree dynamic object reconstruction as a 4D generation problem, eliminating the need for tedious multi-view data collection and camera calibration. This is achieved by leveraging the object-level 3D-aware image diffusion model as the primary supervision signal for training Dynamic Neural Radiance Fields (DyNeRF). Specifically, we propose a Cascade DyNeRF to facilitate stable convergence and temporal continuity under the supervision signal whi"},"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":"2311.02848","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-06T03:26:43Z","cross_cats_sorted":[],"title_canon_sha256":"f9e0a0b97be5ec160c6b80b7b0463f9edfcdf091667cbd1bfe066126a9c74b94","abstract_canon_sha256":"e9221c0127503dae7a8a0410807f5a8e647b930df557a62051c98e579bcf8c22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:18.766155Z","signature_b64":"vz12HEMwNzWRfMyEnrCUoPBEV8Oq2nN8CJkoWEOs/J6zg0ON1TMytBFOZSbyv2gUuIiQ3cMA9pCycUZ4EvN3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbd31a9537fa2a3a3c56c7cbb21297b0f05f4ca14e6694689277c91c7df0e1da","last_reissued_at":"2026-07-05T07:09:18.765735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:18.765735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistent4D: Consistent 360{\\deg} Dynamic Object Generation from Monocular Video","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jin Gao, Li Zhang, Weimin Hu, Yanqin Jiang, Yao Yao","submitted_at":"2023-11-06T03:26:43Z","abstract_excerpt":"In this paper, we present Consistent4D, a novel approach for generating 4D dynamic objects from uncalibrated monocular videos. Uniquely, we cast the 360-degree dynamic object reconstruction as a 4D generation problem, eliminating the need for tedious multi-view data collection and camera calibration. This is achieved by leveraging the object-level 3D-aware image diffusion model as the primary supervision signal for training Dynamic Neural Radiance Fields (DyNeRF). Specifically, we propose a Cascade DyNeRF to facilitate stable convergence and temporal continuity under the supervision signal whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02848","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/2311.02848/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":"2311.02848","created_at":"2026-07-05T07:09:18.765799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.02848v1","created_at":"2026-07-05T07:09:18.765799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02848","created_at":"2026-07-05T07:09:18.765799+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PJRVFJX7IVD","created_at":"2026-07-05T07:09:18.765799+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PJRVFJX7IVDUPCW","created_at":"2026-07-05T07:09:18.765799+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PJRVFJX","created_at":"2026-07-05T07:09:18.765799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25344","citing_title":"Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09187","citing_title":"CP4D: Compositional Physics-aware 4D Scene Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02491","citing_title":"MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents","ref_index":19,"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":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14815","citing_title":"Probing into Camera Control of Video Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26109","citing_title":"Helix4D: Complex 4D Mesh Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30268","citing_title":"PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":300,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13838","citing_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26917","citing_title":"AnimateAnyMesh++: A Flexible 4D Foundation Model for High-Fidelity Text-Driven Mesh Animation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07390","citing_title":"ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D Generation","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PJRVFJX7IVDUPCWY7F3EEUXWD","json":"https://pith.science/pith/7PJRVFJX7IVDUPCWY7F3EEUXWD.json","graph_json":"https://pith.science/api/pith-number/7PJRVFJX7IVDUPCWY7F3EEUXWD/graph.json","events_json":"https://pith.science/api/pith-number/7PJRVFJX7IVDUPCWY7F3EEUXWD/events.json","paper":"https://pith.science/paper/7PJRVFJX"},"agent_actions":{"view_html":"https://pith.science/pith/7PJRVFJX7IVDUPCWY7F3EEUXWD","download_json":"https://pith.science/pith/7PJRVFJX7IVDUPCWY7F3EEUXWD.json","view_paper":"https://pith.science/paper/7PJRVFJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.02848&json=true","fetch_graph":"https://pith.science/api/pith-number/7PJRVFJX7IVDUPCWY7F3EEUXWD/graph.json","fetch_events":"https://pith.science/api/pith-number/7PJRVFJX7IVDUPCWY7F3EEUXWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PJRVFJX7IVDUPCWY7F3EEUXWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PJRVFJX7IVDUPCWY7F3EEUXWD/action/storage_attestation","attest_author":"https://pith.science/pith/7PJRVFJX7IVDUPCWY7F3EEUXWD/action/author_attestation","sign_citation":"https://pith.science/pith/7PJRVFJX7IVDUPCWY7F3EEUXWD/action/citation_signature","submit_replication":"https://pith.science/pith/7PJRVFJX7IVDUPCWY7F3EEUXWD/action/replication_record"}},"created_at":"2026-07-05T07:09:18.765799+00:00","updated_at":"2026-07-05T07:09:18.765799+00:00"}