{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AK4LKUATC3JHHIYITP5T3KDHAM","short_pith_number":"pith:AK4LKUAT","schema_version":"1.0","canonical_sha256":"02b8b5501316d273a3089bfb3da867031cb8326a16d98dc940eeafd8c4f5c4a6","source":{"kind":"arxiv","id":"1812.08351","version":3},"attestation_state":"computed","paper":{"title":"Robustness Meets Deep Learning: An End-to-End Hybrid Pipeline for Unsupervised Learning of Egomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Zihao Zhu, Kostas Daniilidis, Vijay Kumar, Wenxin Liu, Ziyun Wang","submitted_at":"2018-12-20T03:51:47Z","abstract_excerpt":"In this work, we propose a method that combines unsupervised deep learning predictions for optical flow and monocular disparity with a model based optimization procedure for instantaneous camera pose. Given the flow and disparity predictions from the network, we apply a RANSAC outlier rejection scheme to find an inlier set of flows and disparities, which we use to solve for the relative camera pose in a least squares fashion. We show that this pipeline is fully differentiable, allowing us to combine the pose with the network outputs as an additional unsupervised training loss to further refine"},"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":"1812.08351","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-20T03:51:47Z","cross_cats_sorted":[],"title_canon_sha256":"1ad74a936a47d4e51b98f79cdc3c6a47ab51abb087eff9605a33524472fc0b43","abstract_canon_sha256":"ff8d8307d469544f02e9229e5f71c2f4f802fd8652bc9f38efdbcd20c24892ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:06.909074Z","signature_b64":"OKrDBuxtrOAaD1CmD3gRGSzp91qQ+LwVo4myMFeXwIm2yqmivpNDBUeP+hJ3ytoRXP4TAQviSaHJrVaBCVLnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02b8b5501316d273a3089bfb3da867031cb8326a16d98dc940eeafd8c4f5c4a6","last_reissued_at":"2026-05-17T23:54:06.908610Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:06.908610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustness Meets Deep Learning: An End-to-End Hybrid Pipeline for Unsupervised Learning of Egomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Zihao Zhu, Kostas Daniilidis, Vijay Kumar, Wenxin Liu, Ziyun Wang","submitted_at":"2018-12-20T03:51:47Z","abstract_excerpt":"In this work, we propose a method that combines unsupervised deep learning predictions for optical flow and monocular disparity with a model based optimization procedure for instantaneous camera pose. Given the flow and disparity predictions from the network, we apply a RANSAC outlier rejection scheme to find an inlier set of flows and disparities, which we use to solve for the relative camera pose in a least squares fashion. We show that this pipeline is fully differentiable, allowing us to combine the pose with the network outputs as an additional unsupervised training loss to further refine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08351","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":"1812.08351","created_at":"2026-05-17T23:54:06.908679+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.08351v3","created_at":"2026-05-17T23:54:06.908679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08351","created_at":"2026-05-17T23:54:06.908679+00:00"},{"alias_kind":"pith_short_12","alias_value":"AK4LKUATC3JH","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AK4LKUATC3JHHIYI","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AK4LKUAT","created_at":"2026-05-18T12:32:13.499390+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/AK4LKUATC3JHHIYITP5T3KDHAM","json":"https://pith.science/pith/AK4LKUATC3JHHIYITP5T3KDHAM.json","graph_json":"https://pith.science/api/pith-number/AK4LKUATC3JHHIYITP5T3KDHAM/graph.json","events_json":"https://pith.science/api/pith-number/AK4LKUATC3JHHIYITP5T3KDHAM/events.json","paper":"https://pith.science/paper/AK4LKUAT"},"agent_actions":{"view_html":"https://pith.science/pith/AK4LKUATC3JHHIYITP5T3KDHAM","download_json":"https://pith.science/pith/AK4LKUATC3JHHIYITP5T3KDHAM.json","view_paper":"https://pith.science/paper/AK4LKUAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.08351&json=true","fetch_graph":"https://pith.science/api/pith-number/AK4LKUATC3JHHIYITP5T3KDHAM/graph.json","fetch_events":"https://pith.science/api/pith-number/AK4LKUATC3JHHIYITP5T3KDHAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AK4LKUATC3JHHIYITP5T3KDHAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AK4LKUATC3JHHIYITP5T3KDHAM/action/storage_attestation","attest_author":"https://pith.science/pith/AK4LKUATC3JHHIYITP5T3KDHAM/action/author_attestation","sign_citation":"https://pith.science/pith/AK4LKUATC3JHHIYITP5T3KDHAM/action/citation_signature","submit_replication":"https://pith.science/pith/AK4LKUATC3JHHIYITP5T3KDHAM/action/replication_record"}},"created_at":"2026-05-17T23:54:06.908679+00:00","updated_at":"2026-05-17T23:54:06.908679+00:00"}