{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BOCRDFTXLA2PJWAPHFWNFERQQL","short_pith_number":"pith:BOCRDFTX","schema_version":"1.0","canonical_sha256":"0b851196775834f4d80f396cd2923082dd746dea909f6ed33592e70d9837a736","source":{"kind":"arxiv","id":"2504.07093","version":2},"attestation_state":"computed","paper":{"title":"FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Gene Chou, Guandao Yang, Mohamed Abdelfattah, Ning Yu, Noah Snavely, Paul Debevec, Wenqi Xian","submitted_at":"2025-04-09T17:59:31Z","abstract_excerpt":"A versatile video depth estimation model should (1) be accurate and consistent across frames, (2) produce high-resolution depth maps, and (3) support real-time streaming. We propose FlashDepth, a method that satisfies all three requirements, performing depth estimation on a 2044x1148 streaming video at 24 FPS. We show that, with careful modifications to pretrained single-image depth models, these capabilities are enabled with relatively little data and training. We evaluate our approach across multiple unseen datasets against state-of-the-art depth models, and find that ours outperforms them i"},"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":"2504.07093","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-09T17:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"87507137cffce23ca673f000147de838e3e9165f5e04664ae5281911f3cbd5b1","abstract_canon_sha256":"869fb95f5be5ec56618798cd9d1b449a4754041a2a5ae3e4104d2d0d029b65ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:23.814755Z","signature_b64":"ZLZYTWImm7D/4ghza0BYUyJzdBmiMldnDzY0FXQtynEtsw/Z266ma2Kk5wTLFQh5uVUpkp7vbbHcSIZfxpylBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b851196775834f4d80f396cd2923082dd746dea909f6ed33592e70d9837a736","last_reissued_at":"2026-07-05T11:13:23.814207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:23.814207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Gene Chou, Guandao Yang, Mohamed Abdelfattah, Ning Yu, Noah Snavely, Paul Debevec, Wenqi Xian","submitted_at":"2025-04-09T17:59:31Z","abstract_excerpt":"A versatile video depth estimation model should (1) be accurate and consistent across frames, (2) produce high-resolution depth maps, and (3) support real-time streaming. We propose FlashDepth, a method that satisfies all three requirements, performing depth estimation on a 2044x1148 streaming video at 24 FPS. We show that, with careful modifications to pretrained single-image depth models, these capabilities are enabled with relatively little data and training. We evaluate our approach across multiple unseen datasets against state-of-the-art depth models, and find that ours outperforms them i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07093","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/2504.07093/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":"2504.07093","created_at":"2026-07-05T11:13:23.814270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07093v2","created_at":"2026-07-05T11:13:23.814270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07093","created_at":"2026-07-05T11:13:23.814270+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOCRDFTXLA2P","created_at":"2026-07-05T11:13:23.814270+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOCRDFTXLA2PJWAP","created_at":"2026-07-05T11:13:23.814270+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOCRDFTX","created_at":"2026-07-05T11:13:23.814270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25308","citing_title":"Stabilizing Streaming Video Geometry via Dynamic Feature Normalization","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21915","citing_title":"Vista4D: Video Reshooting with 4D Point Clouds","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BOCRDFTXLA2PJWAPHFWNFERQQL","json":"https://pith.science/pith/BOCRDFTXLA2PJWAPHFWNFERQQL.json","graph_json":"https://pith.science/api/pith-number/BOCRDFTXLA2PJWAPHFWNFERQQL/graph.json","events_json":"https://pith.science/api/pith-number/BOCRDFTXLA2PJWAPHFWNFERQQL/events.json","paper":"https://pith.science/paper/BOCRDFTX"},"agent_actions":{"view_html":"https://pith.science/pith/BOCRDFTXLA2PJWAPHFWNFERQQL","download_json":"https://pith.science/pith/BOCRDFTXLA2PJWAPHFWNFERQQL.json","view_paper":"https://pith.science/paper/BOCRDFTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07093&json=true","fetch_graph":"https://pith.science/api/pith-number/BOCRDFTXLA2PJWAPHFWNFERQQL/graph.json","fetch_events":"https://pith.science/api/pith-number/BOCRDFTXLA2PJWAPHFWNFERQQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOCRDFTXLA2PJWAPHFWNFERQQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOCRDFTXLA2PJWAPHFWNFERQQL/action/storage_attestation","attest_author":"https://pith.science/pith/BOCRDFTXLA2PJWAPHFWNFERQQL/action/author_attestation","sign_citation":"https://pith.science/pith/BOCRDFTXLA2PJWAPHFWNFERQQL/action/citation_signature","submit_replication":"https://pith.science/pith/BOCRDFTXLA2PJWAPHFWNFERQQL/action/replication_record"}},"created_at":"2026-07-05T11:13:23.814270+00:00","updated_at":"2026-07-05T11:13:23.814270+00:00"}