{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5M4QAM4UL7EYJH2BJN64SDQGDI","short_pith_number":"pith:5M4QAM4U","schema_version":"1.0","canonical_sha256":"eb390033945fc9849f414b7dc90e061a23e80da6dc4669873a0c20d2dff5498c","source":{"kind":"arxiv","id":"1712.01039","version":2},"attestation_state":"computed","paper":{"title":"Learning for Disparity Estimation through Feature Constancy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengzhu Liu, Jianfeng Zhang, Linbo Qiao, Li Zhou, Wei Chen, Yiliu Feng, Yulan Guo, Zhengfa Liang","submitted_at":"2017-12-04T12:35:38Z","abstract_excerpt":"Stereo matching algorithms usually consist of four steps, including matching cost calculation, matching cost aggregation, disparity calculation, and disparity refinement. Existing CNN-based methods only adopt CNN to solve parts of the four steps, or use different networks to deal with different steps, making them difficult to obtain the overall optimal solution. In this paper, we propose a network architecture to incorporate all steps of stereo matching. The network consists of three parts. The first part calculates the multi-scale shared features. The second part performs matching cost calcul"},"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":"1712.01039","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-04T12:35:38Z","cross_cats_sorted":[],"title_canon_sha256":"763252784de505326c107c5b3671fc983f75eb828dc6514b331bdbca8f2fb817","abstract_canon_sha256":"72a732f531a1836b87439e1605da7acd6880a503b24024cc40ec23a4375bff05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:56.664690Z","signature_b64":"GZuZvlzabRQH/haiGyegix9a83mClrUL1N4XfNhDoInBwXj+mPWMfUtk0Cv1cMuQd+baRF2s38AJzkbUingIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb390033945fc9849f414b7dc90e061a23e80da6dc4669873a0c20d2dff5498c","last_reissued_at":"2026-05-18T00:19:56.664142Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:56.664142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning for Disparity Estimation through Feature Constancy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengzhu Liu, Jianfeng Zhang, Linbo Qiao, Li Zhou, Wei Chen, Yiliu Feng, Yulan Guo, Zhengfa Liang","submitted_at":"2017-12-04T12:35:38Z","abstract_excerpt":"Stereo matching algorithms usually consist of four steps, including matching cost calculation, matching cost aggregation, disparity calculation, and disparity refinement. Existing CNN-based methods only adopt CNN to solve parts of the four steps, or use different networks to deal with different steps, making them difficult to obtain the overall optimal solution. In this paper, we propose a network architecture to incorporate all steps of stereo matching. The network consists of three parts. The first part calculates the multi-scale shared features. The second part performs matching cost calcul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01039","kind":"arxiv","version":2},"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":"1712.01039","created_at":"2026-05-18T00:19:56.664225+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.01039v2","created_at":"2026-05-18T00:19:56.664225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01039","created_at":"2026-05-18T00:19:56.664225+00:00"},{"alias_kind":"pith_short_12","alias_value":"5M4QAM4UL7EY","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"5M4QAM4UL7EYJH2B","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"5M4QAM4U","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.09702","citing_title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5M4QAM4UL7EYJH2BJN64SDQGDI","json":"https://pith.science/pith/5M4QAM4UL7EYJH2BJN64SDQGDI.json","graph_json":"https://pith.science/api/pith-number/5M4QAM4UL7EYJH2BJN64SDQGDI/graph.json","events_json":"https://pith.science/api/pith-number/5M4QAM4UL7EYJH2BJN64SDQGDI/events.json","paper":"https://pith.science/paper/5M4QAM4U"},"agent_actions":{"view_html":"https://pith.science/pith/5M4QAM4UL7EYJH2BJN64SDQGDI","download_json":"https://pith.science/pith/5M4QAM4UL7EYJH2BJN64SDQGDI.json","view_paper":"https://pith.science/paper/5M4QAM4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.01039&json=true","fetch_graph":"https://pith.science/api/pith-number/5M4QAM4UL7EYJH2BJN64SDQGDI/graph.json","fetch_events":"https://pith.science/api/pith-number/5M4QAM4UL7EYJH2BJN64SDQGDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5M4QAM4UL7EYJH2BJN64SDQGDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5M4QAM4UL7EYJH2BJN64SDQGDI/action/storage_attestation","attest_author":"https://pith.science/pith/5M4QAM4UL7EYJH2BJN64SDQGDI/action/author_attestation","sign_citation":"https://pith.science/pith/5M4QAM4UL7EYJH2BJN64SDQGDI/action/citation_signature","submit_replication":"https://pith.science/pith/5M4QAM4UL7EYJH2BJN64SDQGDI/action/replication_record"}},"created_at":"2026-05-18T00:19:56.664225+00:00","updated_at":"2026-05-18T00:19:56.664225+00:00"}