{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KAFGJQR726W5F6BY4QUVJCYJO6","short_pith_number":"pith:KAFGJQR7","schema_version":"1.0","canonical_sha256":"500a64c23fd7add2f838e429548b09778b8796009fc08c9dbecb762fe6867cc6","source":{"kind":"arxiv","id":"2405.02608","version":1},"attestation_state":"computed","paper":{"title":"UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Can Pu, Denis Demandolx, Lei Luo, Rakesh Ranjan, Shuai Yuan, Xiaoyu Xiang, Zhuo Hui","submitted_at":"2024-05-04T08:27:12Z","abstract_excerpt":"Traditional unsupervised optical flow methods are vulnerable to occlusions and motion boundaries due to lack of object-level information. Therefore, we propose UnSAMFlow, an unsupervised flow network that also leverages object information from the latest foundation model Segment Anything Model (SAM). We first include a self-supervised semantic augmentation module tailored to SAM masks. We also analyze the poor gradient landscapes of traditional smoothness losses and propose a new smoothness definition based on homography instead. A simple yet effective mask feature module has also been added t"},"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":"2405.02608","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-04T08:27:12Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"80ad2ca8adcb548ac5a29fc034d448a511ed7450fa0f3f514ec9b903d67f3af4","abstract_canon_sha256":"bcfd9f006236bb4fee65dd9894956f5147aff4f255550ac82ec2332988a5fddb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:18.052781Z","signature_b64":"Ra9r8y2up8PmTKnmN/RN8bY0UkOVS0HL5FUGXYKMCCZ0o+u0ASTLPh4sP31kSsjwv57s/AanffyRzzxJAFmMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"500a64c23fd7add2f838e429548b09778b8796009fc08c9dbecb762fe6867cc6","last_reissued_at":"2026-07-05T08:15:18.052420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:18.052420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Can Pu, Denis Demandolx, Lei Luo, Rakesh Ranjan, Shuai Yuan, Xiaoyu Xiang, Zhuo Hui","submitted_at":"2024-05-04T08:27:12Z","abstract_excerpt":"Traditional unsupervised optical flow methods are vulnerable to occlusions and motion boundaries due to lack of object-level information. Therefore, we propose UnSAMFlow, an unsupervised flow network that also leverages object information from the latest foundation model Segment Anything Model (SAM). We first include a self-supervised semantic augmentation module tailored to SAM masks. We also analyze the poor gradient landscapes of traditional smoothness losses and propose a new smoothness definition based on homography instead. A simple yet effective mask feature module has also been added t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02608","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/2405.02608/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":"2405.02608","created_at":"2026-07-05T08:15:18.052479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02608v1","created_at":"2026-07-05T08:15:18.052479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02608","created_at":"2026-07-05T08:15:18.052479+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAFGJQR726W5","created_at":"2026-07-05T08:15:18.052479+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAFGJQR726W5F6BY","created_at":"2026-07-05T08:15:18.052479+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAFGJQR7","created_at":"2026-07-05T08:15:18.052479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07740","citing_title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","ref_index":86,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAFGJQR726W5F6BY4QUVJCYJO6","json":"https://pith.science/pith/KAFGJQR726W5F6BY4QUVJCYJO6.json","graph_json":"https://pith.science/api/pith-number/KAFGJQR726W5F6BY4QUVJCYJO6/graph.json","events_json":"https://pith.science/api/pith-number/KAFGJQR726W5F6BY4QUVJCYJO6/events.json","paper":"https://pith.science/paper/KAFGJQR7"},"agent_actions":{"view_html":"https://pith.science/pith/KAFGJQR726W5F6BY4QUVJCYJO6","download_json":"https://pith.science/pith/KAFGJQR726W5F6BY4QUVJCYJO6.json","view_paper":"https://pith.science/paper/KAFGJQR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02608&json=true","fetch_graph":"https://pith.science/api/pith-number/KAFGJQR726W5F6BY4QUVJCYJO6/graph.json","fetch_events":"https://pith.science/api/pith-number/KAFGJQR726W5F6BY4QUVJCYJO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAFGJQR726W5F6BY4QUVJCYJO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAFGJQR726W5F6BY4QUVJCYJO6/action/storage_attestation","attest_author":"https://pith.science/pith/KAFGJQR726W5F6BY4QUVJCYJO6/action/author_attestation","sign_citation":"https://pith.science/pith/KAFGJQR726W5F6BY4QUVJCYJO6/action/citation_signature","submit_replication":"https://pith.science/pith/KAFGJQR726W5F6BY4QUVJCYJO6/action/replication_record"}},"created_at":"2026-07-05T08:15:18.052479+00:00","updated_at":"2026-07-05T08:15:18.052479+00:00"}