{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:USEEUGGJGHKOUGWYAI53PSCQVR","short_pith_number":"pith:USEEUGGJ","schema_version":"1.0","canonical_sha256":"a4884a18c931d4ea1ad8023bb7c850ac5b6d86067202b800636b4eb08e9d77dd","source":{"kind":"arxiv","id":"2012.05901","version":2},"attestation_state":"computed","paper":{"title":"Robust Consistent Video Depth Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia-Bin Huang, Johannes Kopf, Xuejian Rong","submitted_at":"2020-12-10T18:59:48Z","abstract_excerpt":"We present an algorithm for estimating consistent dense depth maps and camera poses from a monocular video. We integrate a learning-based depth prior, in the form of a convolutional neural network trained for single-image depth estimation, with geometric optimization, to estimate a smooth camera trajectory as well as detailed and stable depth reconstruction. Our algorithm combines two complementary techniques: (1) flexible deformation-splines for low-frequency large-scale alignment and (2) geometry-aware depth filtering for high-frequency alignment of fine depth details. In contrast to prior a"},"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":"2012.05901","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-10T18:59:48Z","cross_cats_sorted":[],"title_canon_sha256":"85548f5ab4f65cf39c000d38b46a919ab4dffb53c5529c8bc4025bf0eccd379d","abstract_canon_sha256":"bcae7c4de9e624d5d3a5e195e6778ee24c5e9dbff73983f5861eb5c766233dbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:12.502939Z","signature_b64":"yNAeMeaQ6JkLDH23qQJlQsOVmUeZcrTKXohpL+iTrtAY8c0hfF828aUl/iso6WFDnO7teJUsPp4ycG69Z0tMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4884a18c931d4ea1ad8023bb7c850ac5b6d86067202b800636b4eb08e9d77dd","last_reissued_at":"2026-07-05T02:51:12.502460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:12.502460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Consistent Video Depth Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia-Bin Huang, Johannes Kopf, Xuejian Rong","submitted_at":"2020-12-10T18:59:48Z","abstract_excerpt":"We present an algorithm for estimating consistent dense depth maps and camera poses from a monocular video. We integrate a learning-based depth prior, in the form of a convolutional neural network trained for single-image depth estimation, with geometric optimization, to estimate a smooth camera trajectory as well as detailed and stable depth reconstruction. Our algorithm combines two complementary techniques: (1) flexible deformation-splines for low-frequency large-scale alignment and (2) geometry-aware depth filtering for high-frequency alignment of fine depth details. In contrast to prior a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05901","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/2012.05901/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":"2012.05901","created_at":"2026-07-05T02:51:12.502526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.05901v2","created_at":"2026-07-05T02:51:12.502526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05901","created_at":"2026-07-05T02:51:12.502526+00:00"},{"alias_kind":"pith_short_12","alias_value":"USEEUGGJGHKO","created_at":"2026-07-05T02:51:12.502526+00:00"},{"alias_kind":"pith_short_16","alias_value":"USEEUGGJGHKOUGWY","created_at":"2026-07-05T02:51:12.502526+00:00"},{"alias_kind":"pith_short_8","alias_value":"USEEUGGJ","created_at":"2026-07-05T02:51:12.502526+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24718","citing_title":"WildLIFT: Lifting monocular drone video to 3D for species-agnostic wildlife monitoring","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/USEEUGGJGHKOUGWYAI53PSCQVR","json":"https://pith.science/pith/USEEUGGJGHKOUGWYAI53PSCQVR.json","graph_json":"https://pith.science/api/pith-number/USEEUGGJGHKOUGWYAI53PSCQVR/graph.json","events_json":"https://pith.science/api/pith-number/USEEUGGJGHKOUGWYAI53PSCQVR/events.json","paper":"https://pith.science/paper/USEEUGGJ"},"agent_actions":{"view_html":"https://pith.science/pith/USEEUGGJGHKOUGWYAI53PSCQVR","download_json":"https://pith.science/pith/USEEUGGJGHKOUGWYAI53PSCQVR.json","view_paper":"https://pith.science/paper/USEEUGGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.05901&json=true","fetch_graph":"https://pith.science/api/pith-number/USEEUGGJGHKOUGWYAI53PSCQVR/graph.json","fetch_events":"https://pith.science/api/pith-number/USEEUGGJGHKOUGWYAI53PSCQVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USEEUGGJGHKOUGWYAI53PSCQVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USEEUGGJGHKOUGWYAI53PSCQVR/action/storage_attestation","attest_author":"https://pith.science/pith/USEEUGGJGHKOUGWYAI53PSCQVR/action/author_attestation","sign_citation":"https://pith.science/pith/USEEUGGJGHKOUGWYAI53PSCQVR/action/citation_signature","submit_replication":"https://pith.science/pith/USEEUGGJGHKOUGWYAI53PSCQVR/action/replication_record"}},"created_at":"2026-07-05T02:51:12.502526+00:00","updated_at":"2026-07-05T02:51:12.502526+00:00"}