{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6MESSZVIIRHAW566K7NRGOSYLW","short_pith_number":"pith:6MESSZVI","schema_version":"1.0","canonical_sha256":"f3092966a8444e0b77de57db133a585d9bdec0d914ed49e7b8f7353c6a5caa6e","source":{"kind":"arxiv","id":"1711.03665","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liang Zhao, Peng Wang, Ramakant Nevatia, Wei Xu, Zhenheng Yang","submitted_at":"2017-11-10T01:39:29Z","abstract_excerpt":"Learning to reconstruct depths in a single image by watching unlabeled videos via deep convolutional network (DCN) is attracting significant attention in recent years. In this paper, we introduce a surface normal representation for unsupervised depth estimation framework. Our estimated depths are constrained to be compatible with predicted normals, yielding more robust geometry results. Specifically, we formulate an edge-aware depth-normal consistency term, and solve it by constructing a depth-to-normal layer and a normal-to-depth layer inside of the DCN. The depth-to-normal layer takes estima"},"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":"1711.03665","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-10T01:39:29Z","cross_cats_sorted":[],"title_canon_sha256":"8d89d7ccf366b5ec5b77b05b903045d5d1e59e38962491c1641c76a82bb87ea9","abstract_canon_sha256":"b744d963d9fce4961b7151b315197f7219a110a71bd9f270d92e255158f8a88a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:51.753098Z","signature_b64":"17L7GhuxLVb6X/e0xGj7ELYtbB6cEy3plBZHuwbDKOCDCi7hWP2C9AQZt1rJTNYvSABr8i+qYN2q0jzkFumtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3092966a8444e0b77de57db133a585d9bdec0d914ed49e7b8f7353c6a5caa6e","last_reissued_at":"2026-05-18T00:30:51.752490Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:51.752490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liang Zhao, Peng Wang, Ramakant Nevatia, Wei Xu, Zhenheng Yang","submitted_at":"2017-11-10T01:39:29Z","abstract_excerpt":"Learning to reconstruct depths in a single image by watching unlabeled videos via deep convolutional network (DCN) is attracting significant attention in recent years. In this paper, we introduce a surface normal representation for unsupervised depth estimation framework. Our estimated depths are constrained to be compatible with predicted normals, yielding more robust geometry results. Specifically, we formulate an edge-aware depth-normal consistency term, and solve it by constructing a depth-to-normal layer and a normal-to-depth layer inside of the DCN. The depth-to-normal layer takes estima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.03665","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":""},"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":"1711.03665","created_at":"2026-05-18T00:30:51.752578+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.03665v1","created_at":"2026-05-18T00:30:51.752578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.03665","created_at":"2026-05-18T00:30:51.752578+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MESSZVIIRHA","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MESSZVIIRHAW566","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MESSZVI","created_at":"2026-05-18T12:31:03.183658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.08320","citing_title":"Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks","ref_index":83,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MESSZVIIRHAW566K7NRGOSYLW","json":"https://pith.science/pith/6MESSZVIIRHAW566K7NRGOSYLW.json","graph_json":"https://pith.science/api/pith-number/6MESSZVIIRHAW566K7NRGOSYLW/graph.json","events_json":"https://pith.science/api/pith-number/6MESSZVIIRHAW566K7NRGOSYLW/events.json","paper":"https://pith.science/paper/6MESSZVI"},"agent_actions":{"view_html":"https://pith.science/pith/6MESSZVIIRHAW566K7NRGOSYLW","download_json":"https://pith.science/pith/6MESSZVIIRHAW566K7NRGOSYLW.json","view_paper":"https://pith.science/paper/6MESSZVI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.03665&json=true","fetch_graph":"https://pith.science/api/pith-number/6MESSZVIIRHAW566K7NRGOSYLW/graph.json","fetch_events":"https://pith.science/api/pith-number/6MESSZVIIRHAW566K7NRGOSYLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MESSZVIIRHAW566K7NRGOSYLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MESSZVIIRHAW566K7NRGOSYLW/action/storage_attestation","attest_author":"https://pith.science/pith/6MESSZVIIRHAW566K7NRGOSYLW/action/author_attestation","sign_citation":"https://pith.science/pith/6MESSZVIIRHAW566K7NRGOSYLW/action/citation_signature","submit_replication":"https://pith.science/pith/6MESSZVIIRHAW566K7NRGOSYLW/action/replication_record"}},"created_at":"2026-05-18T00:30:51.752578+00:00","updated_at":"2026-05-18T00:30:51.752578+00:00"}