{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Z4UQPMSAHCUKM6DKCONKMBD554","short_pith_number":"pith:Z4UQPMSA","schema_version":"1.0","canonical_sha256":"cf2907b24038a8a6786a139aa6047def2ddeb862843c57d918c5c81f0b4575ed","source":{"kind":"arxiv","id":"1911.13287","version":1},"attestation_state":"computed","paper":{"title":"Domain-invariant Stereo Matching Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjamin Wah, Feihu Zhang, Philip Torr, Ruigang Yang, Victor Prisacariu, Xiaojuan Qi","submitted_at":"2019-11-29T18:41:26Z","abstract_excerpt":"State-of-the-art stereo matching networks have difficulties in generalizing to new unseen environments due to significant domain differences, such as color, illumination, contrast, and texture. In this paper, we aim at designing a domain-invariant stereo matching network (DSMNet) that generalizes well to unseen scenes. To achieve this goal, we propose i) a novel \"domain normalization\" approach that regularizes the distribution of learned representations to allow them to be invariant to domain differences, and ii) a trainable non-local graph-based filter for extracting robust structural and geo"},"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":"1911.13287","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-29T18:41:26Z","cross_cats_sorted":[],"title_canon_sha256":"efb72f25443bc78dcca9b8c8759be72b09b61731b4f2deb484cbb1ef5f5e315b","abstract_canon_sha256":"37a937cc683ec1ba8cadd5dd0651f6ab562367fb90a20115afe42c98bf737377"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:53.679029Z","signature_b64":"XdnStb8gGcB3LX4Wk/WHdaKKRA/zrlhB0wTgpaFjb8uf6EWWnZ/qs+s5k1AU4DLpJq81KYHI2wWhGlhanVklCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf2907b24038a8a6786a139aa6047def2ddeb862843c57d918c5c81f0b4575ed","last_reissued_at":"2026-07-05T00:22:53.678576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:53.678576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-invariant Stereo Matching Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjamin Wah, Feihu Zhang, Philip Torr, Ruigang Yang, Victor Prisacariu, Xiaojuan Qi","submitted_at":"2019-11-29T18:41:26Z","abstract_excerpt":"State-of-the-art stereo matching networks have difficulties in generalizing to new unseen environments due to significant domain differences, such as color, illumination, contrast, and texture. In this paper, we aim at designing a domain-invariant stereo matching network (DSMNet) that generalizes well to unseen scenes. To achieve this goal, we propose i) a novel \"domain normalization\" approach that regularizes the distribution of learned representations to allow them to be invariant to domain differences, and ii) a trainable non-local graph-based filter for extracting robust structural and geo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.13287","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/1911.13287/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":"1911.13287","created_at":"2026-07-05T00:22:53.678640+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.13287v1","created_at":"2026-07-05T00:22:53.678640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.13287","created_at":"2026-07-05T00:22:53.678640+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4UQPMSAHCUK","created_at":"2026-07-05T00:22:53.678640+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4UQPMSAHCUKM6DK","created_at":"2026-07-05T00:22:53.678640+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4UQPMSA","created_at":"2026-07-05T00:22:53.678640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12917","citing_title":"M3D-Stereo: A Multiple-Medium and Multiple-Degradation Dataset for Stereo Image Restoration","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4UQPMSAHCUKM6DKCONKMBD554","json":"https://pith.science/pith/Z4UQPMSAHCUKM6DKCONKMBD554.json","graph_json":"https://pith.science/api/pith-number/Z4UQPMSAHCUKM6DKCONKMBD554/graph.json","events_json":"https://pith.science/api/pith-number/Z4UQPMSAHCUKM6DKCONKMBD554/events.json","paper":"https://pith.science/paper/Z4UQPMSA"},"agent_actions":{"view_html":"https://pith.science/pith/Z4UQPMSAHCUKM6DKCONKMBD554","download_json":"https://pith.science/pith/Z4UQPMSAHCUKM6DKCONKMBD554.json","view_paper":"https://pith.science/paper/Z4UQPMSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.13287&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4UQPMSAHCUKM6DKCONKMBD554/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4UQPMSAHCUKM6DKCONKMBD554/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4UQPMSAHCUKM6DKCONKMBD554/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4UQPMSAHCUKM6DKCONKMBD554/action/storage_attestation","attest_author":"https://pith.science/pith/Z4UQPMSAHCUKM6DKCONKMBD554/action/author_attestation","sign_citation":"https://pith.science/pith/Z4UQPMSAHCUKM6DKCONKMBD554/action/citation_signature","submit_replication":"https://pith.science/pith/Z4UQPMSAHCUKM6DKCONKMBD554/action/replication_record"}},"created_at":"2026-07-05T00:22:53.678640+00:00","updated_at":"2026-07-05T00:22:53.678640+00:00"}