{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3GZM64WMI326RFV4TLAJU7NB73","short_pith_number":"pith:3GZM64WM","schema_version":"1.0","canonical_sha256":"d9b2cf72cc46f5e896bc9ac09a7da1fee0690780f985eec4fcbb615800310884","source":{"kind":"arxiv","id":"1709.02371","version":3},"attestation_state":"computed","paper":{"title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deqing Sun, Jan Kautz, Ming-Yu Liu, Xiaodong Yang","submitted_at":"2017-09-07T17:47:59Z","abstract_excerpt":"We present a compact but effective CNN model for optical flow, called PWC-Net. PWC-Net has been designed according to simple and well-established principles: pyramidal processing, warping, and the use of a cost volume. Cast in a learnable feature pyramid, PWC-Net uses the cur- rent optical flow estimate to warp the CNN features of the second image. It then uses the warped features and features of the first image to construct a cost volume, which is processed by a CNN to estimate the optical flow. PWC-Net is 17 times smaller in size and easier to train than the recent FlowNet2 model. Moreover, "},"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":"1709.02371","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-07T17:47:59Z","cross_cats_sorted":[],"title_canon_sha256":"079d4b915c9a37c37f1c328146b02a3155a9dfa67d21841f5f135da8c6ae26e6","abstract_canon_sha256":"41f23160269f7cacede367cecabe9d0946caa207086439377a55183b81e7f976"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:24.907146Z","signature_b64":"jBu9bNLEhbtf1nzEscekFf97OqCiltFVxJbEE742QUCFiMO6zW7G+UD76+G+1nUlJw9CT5oMJa7Wgmj00W2MDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9b2cf72cc46f5e896bc9ac09a7da1fee0690780f985eec4fcbb615800310884","last_reissued_at":"2026-05-18T00:12:24.906558Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:24.906558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deqing Sun, Jan Kautz, Ming-Yu Liu, Xiaodong Yang","submitted_at":"2017-09-07T17:47:59Z","abstract_excerpt":"We present a compact but effective CNN model for optical flow, called PWC-Net. PWC-Net has been designed according to simple and well-established principles: pyramidal processing, warping, and the use of a cost volume. Cast in a learnable feature pyramid, PWC-Net uses the cur- rent optical flow estimate to warp the CNN features of the second image. It then uses the warped features and features of the first image to construct a cost volume, which is processed by a CNN to estimate the optical flow. PWC-Net is 17 times smaller in size and easier to train than the recent FlowNet2 model. Moreover, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02371","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":""},"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":"1709.02371","created_at":"2026-05-18T00:12:24.906670+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.02371v3","created_at":"2026-05-18T00:12:24.906670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02371","created_at":"2026-05-18T00:12:24.906670+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GZM64WMI326","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GZM64WMI326RFV4","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GZM64WM","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GZM64WMI326RFV4TLAJU7NB73","json":"https://pith.science/pith/3GZM64WMI326RFV4TLAJU7NB73.json","graph_json":"https://pith.science/api/pith-number/3GZM64WMI326RFV4TLAJU7NB73/graph.json","events_json":"https://pith.science/api/pith-number/3GZM64WMI326RFV4TLAJU7NB73/events.json","paper":"https://pith.science/paper/3GZM64WM"},"agent_actions":{"view_html":"https://pith.science/pith/3GZM64WMI326RFV4TLAJU7NB73","download_json":"https://pith.science/pith/3GZM64WMI326RFV4TLAJU7NB73.json","view_paper":"https://pith.science/paper/3GZM64WM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.02371&json=true","fetch_graph":"https://pith.science/api/pith-number/3GZM64WMI326RFV4TLAJU7NB73/graph.json","fetch_events":"https://pith.science/api/pith-number/3GZM64WMI326RFV4TLAJU7NB73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GZM64WMI326RFV4TLAJU7NB73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GZM64WMI326RFV4TLAJU7NB73/action/storage_attestation","attest_author":"https://pith.science/pith/3GZM64WMI326RFV4TLAJU7NB73/action/author_attestation","sign_citation":"https://pith.science/pith/3GZM64WMI326RFV4TLAJU7NB73/action/citation_signature","submit_replication":"https://pith.science/pith/3GZM64WMI326RFV4TLAJU7NB73/action/replication_record"}},"created_at":"2026-05-18T00:12:24.906670+00:00","updated_at":"2026-05-18T00:12:24.906670+00:00"}