{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HCFYXUNLKF5ZRC5DNFTDPEF45N","short_pith_number":"pith:HCFYXUNL","schema_version":"1.0","canonical_sha256":"388b8bd1ab517b988ba369663790bceb7bd8044b97796068ad9c63287ddcc676","source":{"kind":"arxiv","id":"2406.01493","version":4},"attestation_state":"computed","paper":{"title":"Learning Temporally Consistent Video Depth from Video Diffusion Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyu Zhou, Jiahao Shao, Matteo Poggi, Vitor Guizilini, Yiyi Liao, Youmin Zhang, Yuanbo Yang, Yue Wang, Yujun Shen","submitted_at":"2024-06-03T16:20:24Z","abstract_excerpt":"This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal in fostering temporal consistency. Therefore, we reformulate depth prediction into a conditional generation problem to provide contextual information within a clip and across clips. Specifically, we propose a consistent context-aware training and inference strategy for arbitrarily long videos to provide cross-clip context. We sample independent noise levels "},"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":"2406.01493","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T16:20:24Z","cross_cats_sorted":[],"title_canon_sha256":"b120de96e56f4fb3307c0ad3577c6fbacb9f26830835979c4efff27c5deed76d","abstract_canon_sha256":"cc22edd83c14bab5bf0874cc6a96c56e81eaf95568c08328ab1b9ff58bea04cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:33.292138Z","signature_b64":"dRHVOHR4/jEmb3ViR5Qw6F07WcN4aVX3UWgfdfXDI7s5O4aH1uRCz3m3UC8joamGROhR/bEQIgMNwj05d0ouAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"388b8bd1ab517b988ba369663790bceb7bd8044b97796068ad9c63287ddcc676","last_reissued_at":"2026-07-05T11:17:33.291664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:33.291664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Temporally Consistent Video Depth from Video Diffusion Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyu Zhou, Jiahao Shao, Matteo Poggi, Vitor Guizilini, Yiyi Liao, Youmin Zhang, Yuanbo Yang, Yue Wang, Yujun Shen","submitted_at":"2024-06-03T16:20:24Z","abstract_excerpt":"This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal in fostering temporal consistency. Therefore, we reformulate depth prediction into a conditional generation problem to provide contextual information within a clip and across clips. Specifically, we propose a consistent context-aware training and inference strategy for arbitrarily long videos to provide cross-clip context. We sample independent noise levels "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01493","kind":"arxiv","version":4},"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/2406.01493/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":"2406.01493","created_at":"2026-07-05T11:17:33.291726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01493v4","created_at":"2026-07-05T11:17:33.291726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01493","created_at":"2026-07-05T11:17:33.291726+00:00"},{"alias_kind":"pith_short_12","alias_value":"HCFYXUNLKF5Z","created_at":"2026-07-05T11:17:33.291726+00:00"},{"alias_kind":"pith_short_16","alias_value":"HCFYXUNLKF5ZRC5D","created_at":"2026-07-05T11:17:33.291726+00:00"},{"alias_kind":"pith_short_8","alias_value":"HCFYXUNL","created_at":"2026-07-05T11:17:33.291726+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26515","citing_title":"Forget, Anticipate and Adapt: Test Time Training for Long Videos","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26515","citing_title":"Forget, Anticipate and Adapt: Test Time Training for Long Videos","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30060","citing_title":"Towards Consistent Video Geometry Estimation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01099","citing_title":"Geometry-aware 4D Video Generation for Robot Manipulation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2410.03825","citing_title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","ref_index":140,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HCFYXUNLKF5ZRC5DNFTDPEF45N","json":"https://pith.science/pith/HCFYXUNLKF5ZRC5DNFTDPEF45N.json","graph_json":"https://pith.science/api/pith-number/HCFYXUNLKF5ZRC5DNFTDPEF45N/graph.json","events_json":"https://pith.science/api/pith-number/HCFYXUNLKF5ZRC5DNFTDPEF45N/events.json","paper":"https://pith.science/paper/HCFYXUNL"},"agent_actions":{"view_html":"https://pith.science/pith/HCFYXUNLKF5ZRC5DNFTDPEF45N","download_json":"https://pith.science/pith/HCFYXUNLKF5ZRC5DNFTDPEF45N.json","view_paper":"https://pith.science/paper/HCFYXUNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01493&json=true","fetch_graph":"https://pith.science/api/pith-number/HCFYXUNLKF5ZRC5DNFTDPEF45N/graph.json","fetch_events":"https://pith.science/api/pith-number/HCFYXUNLKF5ZRC5DNFTDPEF45N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HCFYXUNLKF5ZRC5DNFTDPEF45N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HCFYXUNLKF5ZRC5DNFTDPEF45N/action/storage_attestation","attest_author":"https://pith.science/pith/HCFYXUNLKF5ZRC5DNFTDPEF45N/action/author_attestation","sign_citation":"https://pith.science/pith/HCFYXUNLKF5ZRC5DNFTDPEF45N/action/citation_signature","submit_replication":"https://pith.science/pith/HCFYXUNLKF5ZRC5DNFTDPEF45N/action/replication_record"}},"created_at":"2026-07-05T11:17:33.291726+00:00","updated_at":"2026-07-05T11:17:33.291726+00:00"}