{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ILA4RGM7L27M57XR4ADJHPTMHX","short_pith_number":"pith:ILA4RGM7","schema_version":"1.0","canonical_sha256":"42c1c8999f5ebecefef1e00693be6c3dca70a92d1f8696c58a14949239e3e0e8","source":{"kind":"arxiv","id":"2503.05549","version":3},"attestation_state":"computed","paper":{"title":"Stereo Any Video: Temporally Consistent Stereo Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junpeng Jing, Krystian Mikolajczyk, Weixun Luo, Ye Mao","submitted_at":"2025-03-07T16:20:36Z","abstract_excerpt":"This paper introduces Stereo Any Video, a powerful framework for video stereo matching. It can estimate spatially accurate and temporally consistent disparities without relying on auxiliary information such as camera poses or optical flow. The strong capability is driven by rich priors from monocular video depth models, which are integrated with convolutional features to produce stable representations. To further enhance performance, key architectural innovations are introduced: all-to-all-pairs correlation, which constructs smooth and robust matching cost volumes, and temporal convex upsampli"},"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":"2503.05549","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-07T16:20:36Z","cross_cats_sorted":[],"title_canon_sha256":"e31154a388aa8b039a2321de3c6b434f84cc3d81a46c1a5ec14538c274a9779f","abstract_canon_sha256":"1fb3c379e7b3faba1e3052d2241481adf4824d7ed7cbac3fb69e7be353e9361a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:33.477866Z","signature_b64":"Sp0DUYqdeSNsylNj2GJJyf91OVd080kQTjj3zgPmTOcG1UvcbL6cWCZ8whYeZAejK/QFf6gJNVle60l/SeF5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42c1c8999f5ebecefef1e00693be6c3dca70a92d1f8696c58a14949239e3e0e8","last_reissued_at":"2026-07-05T11:40:33.477432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:33.477432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stereo Any Video: Temporally Consistent Stereo Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junpeng Jing, Krystian Mikolajczyk, Weixun Luo, Ye Mao","submitted_at":"2025-03-07T16:20:36Z","abstract_excerpt":"This paper introduces Stereo Any Video, a powerful framework for video stereo matching. It can estimate spatially accurate and temporally consistent disparities without relying on auxiliary information such as camera poses or optical flow. The strong capability is driven by rich priors from monocular video depth models, which are integrated with convolutional features to produce stable representations. To further enhance performance, key architectural innovations are introduced: all-to-all-pairs correlation, which constructs smooth and robust matching cost volumes, and temporal convex upsampli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05549","kind":"arxiv","version":3},"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/2503.05549/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":"2503.05549","created_at":"2026-07-05T11:40:33.477486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.05549v3","created_at":"2026-07-05T11:40:33.477486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05549","created_at":"2026-07-05T11:40:33.477486+00:00"},{"alias_kind":"pith_short_12","alias_value":"ILA4RGM7L27M","created_at":"2026-07-05T11:40:33.477486+00:00"},{"alias_kind":"pith_short_16","alias_value":"ILA4RGM7L27M57XR","created_at":"2026-07-05T11:40:33.477486+00:00"},{"alias_kind":"pith_short_8","alias_value":"ILA4RGM7","created_at":"2026-07-05T11:40:33.477486+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22971","citing_title":"Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ILA4RGM7L27M57XR4ADJHPTMHX","json":"https://pith.science/pith/ILA4RGM7L27M57XR4ADJHPTMHX.json","graph_json":"https://pith.science/api/pith-number/ILA4RGM7L27M57XR4ADJHPTMHX/graph.json","events_json":"https://pith.science/api/pith-number/ILA4RGM7L27M57XR4ADJHPTMHX/events.json","paper":"https://pith.science/paper/ILA4RGM7"},"agent_actions":{"view_html":"https://pith.science/pith/ILA4RGM7L27M57XR4ADJHPTMHX","download_json":"https://pith.science/pith/ILA4RGM7L27M57XR4ADJHPTMHX.json","view_paper":"https://pith.science/paper/ILA4RGM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.05549&json=true","fetch_graph":"https://pith.science/api/pith-number/ILA4RGM7L27M57XR4ADJHPTMHX/graph.json","fetch_events":"https://pith.science/api/pith-number/ILA4RGM7L27M57XR4ADJHPTMHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ILA4RGM7L27M57XR4ADJHPTMHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ILA4RGM7L27M57XR4ADJHPTMHX/action/storage_attestation","attest_author":"https://pith.science/pith/ILA4RGM7L27M57XR4ADJHPTMHX/action/author_attestation","sign_citation":"https://pith.science/pith/ILA4RGM7L27M57XR4ADJHPTMHX/action/citation_signature","submit_replication":"https://pith.science/pith/ILA4RGM7L27M57XR4ADJHPTMHX/action/replication_record"}},"created_at":"2026-07-05T11:40:33.477486+00:00","updated_at":"2026-07-05T11:40:33.477486+00:00"}