{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SIJR5SSIKRFUJARLCLBKYKRMNN","short_pith_number":"pith:SIJR5SSI","schema_version":"1.0","canonical_sha256":"92131eca48544b44822b12c2ac2a2c6b66cf686e418ad2aa20e752b64a485518","source":{"kind":"arxiv","id":"2210.16900","version":1},"attestation_state":"computed","paper":{"title":"High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andr\\'es Bruhn, Azin Jahedi, Lukas Mehl, Marc Rivinius, Maximilian Luz","submitted_at":"2022-10-30T17:48:11Z","abstract_excerpt":"In this report, we present our optical flow approach, MS-RAFT+, that won the Robust Vision Challenge 2022. It is based on the MS-RAFT method, which successfully integrates several multi-scale concepts into single-scale RAFT. Our approach extends this method by exploiting an additional finer scale for estimating the flow, which is made feasible by on-demand cost computation. This way, it can not only operate at half the original resolution, but also use MS-RAFT's shared convex upsampler to obtain full resolution flow. Moreover, our approach relies on an adjusted fine-tuning scheme during traini"},"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":"2210.16900","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-30T17:48:11Z","cross_cats_sorted":[],"title_canon_sha256":"9dd26726c26f6717d96bdbd149c10795f84a59fd0ef89b30083165ba69328437","abstract_canon_sha256":"e15a90fee599bf69bdf1da093d6a8cf5112ea007421dc8e837a05584a9c40ffd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:19.593231Z","signature_b64":"E2l5ymwsmyBjkMynAr6ibMr+uHICcHUybjK8Yb9Y8cJVQM0gmZA39NZGigO6gc7x0Oqguq1wkLlP4H0uNrYkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92131eca48544b44822b12c2ac2a2c6b66cf686e418ad2aa20e752b64a485518","last_reissued_at":"2026-07-05T11:11:19.592658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:19.592658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andr\\'es Bruhn, Azin Jahedi, Lukas Mehl, Marc Rivinius, Maximilian Luz","submitted_at":"2022-10-30T17:48:11Z","abstract_excerpt":"In this report, we present our optical flow approach, MS-RAFT+, that won the Robust Vision Challenge 2022. It is based on the MS-RAFT method, which successfully integrates several multi-scale concepts into single-scale RAFT. Our approach extends this method by exploiting an additional finer scale for estimating the flow, which is made feasible by on-demand cost computation. This way, it can not only operate at half the original resolution, but also use MS-RAFT's shared convex upsampler to obtain full resolution flow. Moreover, our approach relies on an adjusted fine-tuning scheme during traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16900","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/2210.16900/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":"2210.16900","created_at":"2026-07-05T11:11:19.592718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16900v1","created_at":"2026-07-05T11:11:19.592718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16900","created_at":"2026-07-05T11:11:19.592718+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIJR5SSIKRFU","created_at":"2026-07-05T11:11:19.592718+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIJR5SSIKRFUJARL","created_at":"2026-07-05T11:11:19.592718+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIJR5SSI","created_at":"2026-07-05T11:11:19.592718+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29220","citing_title":"Motion-guided sparse correction enables expert-quality point tracking across diverse microscopy regimes","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01383","citing_title":"CaRLi-V: Camera-RADAR-LiDAR Point-Wise 3D Velocity Estimation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIJR5SSIKRFUJARLCLBKYKRMNN","json":"https://pith.science/pith/SIJR5SSIKRFUJARLCLBKYKRMNN.json","graph_json":"https://pith.science/api/pith-number/SIJR5SSIKRFUJARLCLBKYKRMNN/graph.json","events_json":"https://pith.science/api/pith-number/SIJR5SSIKRFUJARLCLBKYKRMNN/events.json","paper":"https://pith.science/paper/SIJR5SSI"},"agent_actions":{"view_html":"https://pith.science/pith/SIJR5SSIKRFUJARLCLBKYKRMNN","download_json":"https://pith.science/pith/SIJR5SSIKRFUJARLCLBKYKRMNN.json","view_paper":"https://pith.science/paper/SIJR5SSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16900&json=true","fetch_graph":"https://pith.science/api/pith-number/SIJR5SSIKRFUJARLCLBKYKRMNN/graph.json","fetch_events":"https://pith.science/api/pith-number/SIJR5SSIKRFUJARLCLBKYKRMNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIJR5SSIKRFUJARLCLBKYKRMNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIJR5SSIKRFUJARLCLBKYKRMNN/action/storage_attestation","attest_author":"https://pith.science/pith/SIJR5SSIKRFUJARLCLBKYKRMNN/action/author_attestation","sign_citation":"https://pith.science/pith/SIJR5SSIKRFUJARLCLBKYKRMNN/action/citation_signature","submit_replication":"https://pith.science/pith/SIJR5SSIKRFUJARLCLBKYKRMNN/action/replication_record"}},"created_at":"2026-07-05T11:11:19.592718+00:00","updated_at":"2026-07-05T11:11:19.592718+00:00"}