{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:57AQOK4SPP5HUGHUFN7OLQKG4Z","short_pith_number":"pith:57AQOK4S","schema_version":"1.0","canonical_sha256":"efc1072b927bfa7a18f42b7ee5c146e679ed2f44b3ee3322cf861315e5dba9f6","source":{"kind":"arxiv","id":"2509.05297","version":1},"attestation_state":"computed","paper":{"title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabio Tosi, Matteo Poggi","submitted_at":"2025-09-05T17:59:59Z","abstract_excerpt":"We present FlowSeek, a novel framework for optical flow requiring minimal hardware resources for training. FlowSeek marries the latest advances on the design space of optical flow networks with cutting-edge single-image depth foundation models and classical low-dimensional motion parametrization, implementing a compact, yet accurate architecture. FlowSeek is trained on a single consumer-grade GPU, a hardware budget about 8x lower compared to most recent methods, and still achieves superior cross-dataset generalization on Sintel Final and KITTI, with a relative improvement of 10 and 15% over th"},"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":"2509.05297","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-05T17:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"bc34342a736e76dcf04fd5175e4521a8b712fbfee2a7885e20055cb0512b2c5f","abstract_canon_sha256":"88051fa729b52455abf635568f1d28dc270301fc60aee6befff3e0d5636e092e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:39.084444Z","signature_b64":"aCY7QjvbVdKLKh2sENfO/ukvD/WU92huA8EWi9uXHlcLKicXjeFA7RdvbFZNt+5VvZHTlaIUuXLecU7lIzxfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efc1072b927bfa7a18f42b7ee5c146e679ed2f44b3ee3322cf861315e5dba9f6","last_reissued_at":"2026-07-05T12:05:39.083958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:39.083958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabio Tosi, Matteo Poggi","submitted_at":"2025-09-05T17:59:59Z","abstract_excerpt":"We present FlowSeek, a novel framework for optical flow requiring minimal hardware resources for training. FlowSeek marries the latest advances on the design space of optical flow networks with cutting-edge single-image depth foundation models and classical low-dimensional motion parametrization, implementing a compact, yet accurate architecture. FlowSeek is trained on a single consumer-grade GPU, a hardware budget about 8x lower compared to most recent methods, and still achieves superior cross-dataset generalization on Sintel Final and KITTI, with a relative improvement of 10 and 15% over th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05297","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/2509.05297/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":"2509.05297","created_at":"2026-07-05T12:05:39.084015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05297v1","created_at":"2026-07-05T12:05:39.084015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05297","created_at":"2026-07-05T12:05:39.084015+00:00"},{"alias_kind":"pith_short_12","alias_value":"57AQOK4SPP5H","created_at":"2026-07-05T12:05:39.084015+00:00"},{"alias_kind":"pith_short_16","alias_value":"57AQOK4SPP5HUGHU","created_at":"2026-07-05T12:05:39.084015+00:00"},{"alias_kind":"pith_short_8","alias_value":"57AQOK4S","created_at":"2026-07-05T12:05:39.084015+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24282","citing_title":"UniRED: Unified RGB-D Video Frame Interpolation with Event Guidance","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57AQOK4SPP5HUGHUFN7OLQKG4Z","json":"https://pith.science/pith/57AQOK4SPP5HUGHUFN7OLQKG4Z.json","graph_json":"https://pith.science/api/pith-number/57AQOK4SPP5HUGHUFN7OLQKG4Z/graph.json","events_json":"https://pith.science/api/pith-number/57AQOK4SPP5HUGHUFN7OLQKG4Z/events.json","paper":"https://pith.science/paper/57AQOK4S"},"agent_actions":{"view_html":"https://pith.science/pith/57AQOK4SPP5HUGHUFN7OLQKG4Z","download_json":"https://pith.science/pith/57AQOK4SPP5HUGHUFN7OLQKG4Z.json","view_paper":"https://pith.science/paper/57AQOK4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05297&json=true","fetch_graph":"https://pith.science/api/pith-number/57AQOK4SPP5HUGHUFN7OLQKG4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/57AQOK4SPP5HUGHUFN7OLQKG4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57AQOK4SPP5HUGHUFN7OLQKG4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57AQOK4SPP5HUGHUFN7OLQKG4Z/action/storage_attestation","attest_author":"https://pith.science/pith/57AQOK4SPP5HUGHUFN7OLQKG4Z/action/author_attestation","sign_citation":"https://pith.science/pith/57AQOK4SPP5HUGHUFN7OLQKG4Z/action/citation_signature","submit_replication":"https://pith.science/pith/57AQOK4SPP5HUGHUFN7OLQKG4Z/action/replication_record"}},"created_at":"2026-07-05T12:05:39.084015+00:00","updated_at":"2026-07-05T12:05:39.084015+00:00"}