{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XA5JZEJTTV7MSJZXMQMNVN73PA","short_pith_number":"pith:XA5JZEJT","schema_version":"1.0","canonical_sha256":"b83a9c91339d7ec927376418dab7fb781eec667f2ffd3bc002418c0709ba9716","source":{"kind":"arxiv","id":"2504.01016","version":1},"attestation_state":"computed","paper":{"title":"GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.GR","authors_text":"Song-Hai Zhang, Tian-Xing Xu, Wenbo Hu, Xiangjun Gao, Xiaoyu Li, Ying Shan","submitted_at":"2025-04-01T17:58:03Z","abstract_excerpt":"Despite remarkable advancements in video depth estimation, existing methods exhibit inherent limitations in achieving geometric fidelity through the affine-invariant predictions, limiting their applicability in reconstruction and other metrically grounded downstream tasks. We propose GeometryCrafter, a novel framework that recovers high-fidelity point map sequences with temporal coherence from open-world videos, enabling accurate 3D/4D reconstruction, camera parameter estimation, and other depth-based applications. At the core of our approach lies a point map Variational Autoencoder (VAE) that"},"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":"2504.01016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2025-04-01T17:58:03Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"3af8fa43b65c17524882a94665baa12f6eee11a8ec165ae9aa67fb6eef2c1a7c","abstract_canon_sha256":"fa7689eab37f6dbbbca7e4127b8a168c83ed81587608c631150922ff66efa7dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:54.901966Z","signature_b64":"V38St9/hkPWwAll8BibBDjMJxQPXS64DMz7iCBHjOEEi4Y211x7bhjGWtLzmmiyXym9n4PsIu0urEscZRF4hAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b83a9c91339d7ec927376418dab7fb781eec667f2ffd3bc002418c0709ba9716","last_reissued_at":"2026-07-05T10:42:54.901403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:54.901403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.GR","authors_text":"Song-Hai Zhang, Tian-Xing Xu, Wenbo Hu, Xiangjun Gao, Xiaoyu Li, Ying Shan","submitted_at":"2025-04-01T17:58:03Z","abstract_excerpt":"Despite remarkable advancements in video depth estimation, existing methods exhibit inherent limitations in achieving geometric fidelity through the affine-invariant predictions, limiting their applicability in reconstruction and other metrically grounded downstream tasks. We propose GeometryCrafter, a novel framework that recovers high-fidelity point map sequences with temporal coherence from open-world videos, enabling accurate 3D/4D reconstruction, camera parameter estimation, and other depth-based applications. At the core of our approach lies a point map Variational Autoencoder (VAE) that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01016","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/2504.01016/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":"2504.01016","created_at":"2026-07-05T10:42:54.901474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01016v1","created_at":"2026-07-05T10:42:54.901474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01016","created_at":"2026-07-05T10:42:54.901474+00:00"},{"alias_kind":"pith_short_12","alias_value":"XA5JZEJTTV7M","created_at":"2026-07-05T10:42:54.901474+00:00"},{"alias_kind":"pith_short_16","alias_value":"XA5JZEJTTV7MSJZX","created_at":"2026-07-05T10:42:54.901474+00:00"},{"alias_kind":"pith_short_8","alias_value":"XA5JZEJT","created_at":"2026-07-05T10:42:54.901474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00832","citing_title":"Pano2World: End-to-End 3D Generation via Unified Multi-View Sequences","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23888","citing_title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17568","citing_title":"PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12494","citing_title":"Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction","ref_index":78,"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":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XA5JZEJTTV7MSJZXMQMNVN73PA","json":"https://pith.science/pith/XA5JZEJTTV7MSJZXMQMNVN73PA.json","graph_json":"https://pith.science/api/pith-number/XA5JZEJTTV7MSJZXMQMNVN73PA/graph.json","events_json":"https://pith.science/api/pith-number/XA5JZEJTTV7MSJZXMQMNVN73PA/events.json","paper":"https://pith.science/paper/XA5JZEJT"},"agent_actions":{"view_html":"https://pith.science/pith/XA5JZEJTTV7MSJZXMQMNVN73PA","download_json":"https://pith.science/pith/XA5JZEJTTV7MSJZXMQMNVN73PA.json","view_paper":"https://pith.science/paper/XA5JZEJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01016&json=true","fetch_graph":"https://pith.science/api/pith-number/XA5JZEJTTV7MSJZXMQMNVN73PA/graph.json","fetch_events":"https://pith.science/api/pith-number/XA5JZEJTTV7MSJZXMQMNVN73PA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XA5JZEJTTV7MSJZXMQMNVN73PA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XA5JZEJTTV7MSJZXMQMNVN73PA/action/storage_attestation","attest_author":"https://pith.science/pith/XA5JZEJTTV7MSJZXMQMNVN73PA/action/author_attestation","sign_citation":"https://pith.science/pith/XA5JZEJTTV7MSJZXMQMNVN73PA/action/citation_signature","submit_replication":"https://pith.science/pith/XA5JZEJTTV7MSJZXMQMNVN73PA/action/replication_record"}},"created_at":"2026-07-05T10:42:54.901474+00:00","updated_at":"2026-07-05T10:42:54.901474+00:00"}