{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CXCTYTZGFNMHWM33J2IAPJKVQB","short_pith_number":"pith:CXCTYTZG","schema_version":"1.0","canonical_sha256":"15c53c4f262b587b337b4e9007a5558073fd91d7e5c8cd60f3696ff4dae9e8ac","source":{"kind":"arxiv","id":"2504.07961","version":2},"attestation_state":"computed","paper":{"title":"Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Chuanxia Zheng, Diane Larlus, Iro Laina, Zeren Jiang","submitted_at":"2025-04-10T17:59:55Z","abstract_excerpt":"We introduce Geo4D, a method to repurpose video diffusion models for monocular 3D reconstruction of dynamic scenes. By leveraging the strong dynamic priors captured by large-scale pre-trained video models, Geo4D can be trained using only synthetic data while generalizing well to real data in a zero-shot manner. Geo4D predicts several complementary geometric modalities, namely point, disparity, and ray maps. We propose a new multi-modal alignment algorithm to align and fuse these modalities, as well as a sliding window approach at inference time, thus enabling robust and accurate 4D reconstruct"},"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":"2504.07961","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"99c15c9061ef959e5ab58687f167e893458460dad27ab16648cf9e08f5f56fea","abstract_canon_sha256":"e4f7bbba7006609aa9bb41efd0edbd492010195bb00866f32458375d2ad86ec4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:03.011726Z","signature_b64":"Uovm7MF2or8BFE0apIpOOLup2ILVe1jHALkYytXZkSGdqs2+5858alMGVAiUaWnoSq7EI6nQTUhu/33UkPy+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15c53c4f262b587b337b4e9007a5558073fd91d7e5c8cd60f3696ff4dae9e8ac","last_reissued_at":"2026-07-05T11:56:03.011225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:03.011225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Chuanxia Zheng, Diane Larlus, Iro Laina, Zeren Jiang","submitted_at":"2025-04-10T17:59:55Z","abstract_excerpt":"We introduce Geo4D, a method to repurpose video diffusion models for monocular 3D reconstruction of dynamic scenes. By leveraging the strong dynamic priors captured by large-scale pre-trained video models, Geo4D can be trained using only synthetic data while generalizing well to real data in a zero-shot manner. Geo4D predicts several complementary geometric modalities, namely point, disparity, and ray maps. We propose a new multi-modal alignment algorithm to align and fuse these modalities, as well as a sliding window approach at inference time, thus enabling robust and accurate 4D reconstruct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07961","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/2504.07961/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":"2504.07961","created_at":"2026-07-05T11:56:03.011283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07961v2","created_at":"2026-07-05T11:56:03.011283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07961","created_at":"2026-07-05T11:56:03.011283+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXCTYTZGFNMH","created_at":"2026-07-05T11:56:03.011283+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXCTYTZGFNMHWM33","created_at":"2026-07-05T11:56:03.011283+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXCTYTZG","created_at":"2026-07-05T11:56:03.011283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03943","citing_title":"PointAction: 3D Points as Universal Action Representations for Robot Control","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17623","citing_title":"ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07982","citing_title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17568","citing_title":"PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00658","citing_title":"UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21915","citing_title":"Vista4D: Video Reshooting with 4D Point Clouds","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17623","citing_title":"ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CXCTYTZGFNMHWM33J2IAPJKVQB","json":"https://pith.science/pith/CXCTYTZGFNMHWM33J2IAPJKVQB.json","graph_json":"https://pith.science/api/pith-number/CXCTYTZGFNMHWM33J2IAPJKVQB/graph.json","events_json":"https://pith.science/api/pith-number/CXCTYTZGFNMHWM33J2IAPJKVQB/events.json","paper":"https://pith.science/paper/CXCTYTZG"},"agent_actions":{"view_html":"https://pith.science/pith/CXCTYTZGFNMHWM33J2IAPJKVQB","download_json":"https://pith.science/pith/CXCTYTZGFNMHWM33J2IAPJKVQB.json","view_paper":"https://pith.science/paper/CXCTYTZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07961&json=true","fetch_graph":"https://pith.science/api/pith-number/CXCTYTZGFNMHWM33J2IAPJKVQB/graph.json","fetch_events":"https://pith.science/api/pith-number/CXCTYTZGFNMHWM33J2IAPJKVQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXCTYTZGFNMHWM33J2IAPJKVQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXCTYTZGFNMHWM33J2IAPJKVQB/action/storage_attestation","attest_author":"https://pith.science/pith/CXCTYTZGFNMHWM33J2IAPJKVQB/action/author_attestation","sign_citation":"https://pith.science/pith/CXCTYTZGFNMHWM33J2IAPJKVQB/action/citation_signature","submit_replication":"https://pith.science/pith/CXCTYTZGFNMHWM33J2IAPJKVQB/action/replication_record"}},"created_at":"2026-07-05T11:56:03.011283+00:00","updated_at":"2026-07-05T11:56:03.011283+00:00"}