{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:46WRWXDAP4G2N24W4JWVZI6CJG","short_pith_number":"pith:46WRWXDA","schema_version":"1.0","canonical_sha256":"e7ad1b5c607f0da6eb96e26d5ca3c249b8fa925e23ab177373b47a2e9616ec07","source":{"kind":"arxiv","id":"2205.08668","version":1},"attestation_state":"computed","paper":{"title":"Learning Monocular Depth Estimation via Selective Distillation of Stereo Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kuk-Jin Yoon, Kyeongseob Song","submitted_at":"2022-05-18T00:34:28Z","abstract_excerpt":"Monocular depth estimation has been extensively explored based on deep learning, yet its accuracy and generalization ability still lag far behind the stereo-based methods. To tackle this, a few recent studies have proposed to supervise the monocular depth estimation network by distilling disparity maps as proxy ground-truths. However, these studies naively distill the stereo knowledge without considering the comparative advantages of stereo-based and monocular depth estimation methods. In this paper, we propose to selectively distill the disparity maps for more reliable proxy supervision. Spec"},"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":"2205.08668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-18T00:34:28Z","cross_cats_sorted":[],"title_canon_sha256":"1e1f30dba4430c87935ff7208721f8ddcd9754fd2d6ffff5f0be61427a96f837","abstract_canon_sha256":"43e98ef0949fcd75817598c0946dbf716d9ba08d3d2d52687ad5539578016507"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:27.742497Z","signature_b64":"483nJe1O6EdV3auzs+J7E+XxCBEeMJPkMKtr6PlwMzCwPzS3MaKf+IY8zfwsOCf8CGeqb3ESOIx9YeovMj1hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7ad1b5c607f0da6eb96e26d5ca3c249b8fa925e23ab177373b47a2e9616ec07","last_reissued_at":"2026-07-05T04:24:27.742058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:27.742058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Monocular Depth Estimation via Selective Distillation of Stereo Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kuk-Jin Yoon, Kyeongseob Song","submitted_at":"2022-05-18T00:34:28Z","abstract_excerpt":"Monocular depth estimation has been extensively explored based on deep learning, yet its accuracy and generalization ability still lag far behind the stereo-based methods. To tackle this, a few recent studies have proposed to supervise the monocular depth estimation network by distilling disparity maps as proxy ground-truths. However, these studies naively distill the stereo knowledge without considering the comparative advantages of stereo-based and monocular depth estimation methods. In this paper, we propose to selectively distill the disparity maps for more reliable proxy supervision. Spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08668","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/2205.08668/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":"2205.08668","created_at":"2026-07-05T04:24:27.742119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.08668v1","created_at":"2026-07-05T04:24:27.742119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08668","created_at":"2026-07-05T04:24:27.742119+00:00"},{"alias_kind":"pith_short_12","alias_value":"46WRWXDAP4G2","created_at":"2026-07-05T04:24:27.742119+00:00"},{"alias_kind":"pith_short_16","alias_value":"46WRWXDAP4G2N24W","created_at":"2026-07-05T04:24:27.742119+00:00"},{"alias_kind":"pith_short_8","alias_value":"46WRWXDA","created_at":"2026-07-05T04:24:27.742119+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/46WRWXDAP4G2N24W4JWVZI6CJG","json":"https://pith.science/pith/46WRWXDAP4G2N24W4JWVZI6CJG.json","graph_json":"https://pith.science/api/pith-number/46WRWXDAP4G2N24W4JWVZI6CJG/graph.json","events_json":"https://pith.science/api/pith-number/46WRWXDAP4G2N24W4JWVZI6CJG/events.json","paper":"https://pith.science/paper/46WRWXDA"},"agent_actions":{"view_html":"https://pith.science/pith/46WRWXDAP4G2N24W4JWVZI6CJG","download_json":"https://pith.science/pith/46WRWXDAP4G2N24W4JWVZI6CJG.json","view_paper":"https://pith.science/paper/46WRWXDA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.08668&json=true","fetch_graph":"https://pith.science/api/pith-number/46WRWXDAP4G2N24W4JWVZI6CJG/graph.json","fetch_events":"https://pith.science/api/pith-number/46WRWXDAP4G2N24W4JWVZI6CJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46WRWXDAP4G2N24W4JWVZI6CJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46WRWXDAP4G2N24W4JWVZI6CJG/action/storage_attestation","attest_author":"https://pith.science/pith/46WRWXDAP4G2N24W4JWVZI6CJG/action/author_attestation","sign_citation":"https://pith.science/pith/46WRWXDAP4G2N24W4JWVZI6CJG/action/citation_signature","submit_replication":"https://pith.science/pith/46WRWXDAP4G2N24W4JWVZI6CJG/action/replication_record"}},"created_at":"2026-07-05T04:24:27.742119+00:00","updated_at":"2026-07-05T04:24:27.742119+00:00"}