{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SZQY77TQBVA3ARPWA7GDOUBADO","short_pith_number":"pith:SZQY77TQ","schema_version":"1.0","canonical_sha256":"96618ffe700d41b045f607cc3750201baaad41b0a3ed12d6625b16d9a535049c","source":{"kind":"arxiv","id":"2501.12824","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Monocular Depth Estimation with Multi-Source Auxiliary Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abigail Morrison, Alessio Quercia, Erenus Yildiz, Hanno Scharr, Ira Assent, Kai Krajsek, Zhuo Cao","submitted_at":"2025-01-22T12:04:58Z","abstract_excerpt":"Monocular depth estimation (MDE) is a challenging task in computer vision, often hindered by the cost and scarcity of high-quality labeled datasets. We tackle this challenge using auxiliary datasets from related vision tasks for an alternating training scheme with a shared decoder built on top of a pre-trained vision foundation model, while giving a higher weight to MDE. Through extensive experiments we demonstrate the benefits of incorporating various in-domain auxiliary datasets and tasks to improve MDE quality on average by ~11%. Our experimental analysis shows that auxiliary tasks have dif"},"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":"2501.12824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-22T12:04:58Z","cross_cats_sorted":[],"title_canon_sha256":"24cf4b0453ef7bd14f306f7f24ec9501ca86e62b1e11001579b06cac1cf80326","abstract_canon_sha256":"a6b5e8f7678fd83a42c4b23d38d6c175e9251ea79a250babc26d54546036499e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:35.520149Z","signature_b64":"FNsp61c6dlEOF4R5hQQ4rzCciTyb28G/KvlNqtxUz0wdcjCo9fTp4N9RzOFcQnOGQJtgGREiUfRq+ufnWyxSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96618ffe700d41b045f607cc3750201baaad41b0a3ed12d6625b16d9a535049c","last_reissued_at":"2026-07-05T10:47:35.519694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:35.519694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Monocular Depth Estimation with Multi-Source Auxiliary Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abigail Morrison, Alessio Quercia, Erenus Yildiz, Hanno Scharr, Ira Assent, Kai Krajsek, Zhuo Cao","submitted_at":"2025-01-22T12:04:58Z","abstract_excerpt":"Monocular depth estimation (MDE) is a challenging task in computer vision, often hindered by the cost and scarcity of high-quality labeled datasets. We tackle this challenge using auxiliary datasets from related vision tasks for an alternating training scheme with a shared decoder built on top of a pre-trained vision foundation model, while giving a higher weight to MDE. Through extensive experiments we demonstrate the benefits of incorporating various in-domain auxiliary datasets and tasks to improve MDE quality on average by ~11%. Our experimental analysis shows that auxiliary tasks have dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12824","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/2501.12824/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":"2501.12824","created_at":"2026-07-05T10:47:35.519753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12824v1","created_at":"2026-07-05T10:47:35.519753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12824","created_at":"2026-07-05T10:47:35.519753+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZQY77TQBVA3","created_at":"2026-07-05T10:47:35.519753+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZQY77TQBVA3ARPW","created_at":"2026-07-05T10:47:35.519753+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZQY77TQ","created_at":"2026-07-05T10:47:35.519753+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/SZQY77TQBVA3ARPWA7GDOUBADO","json":"https://pith.science/pith/SZQY77TQBVA3ARPWA7GDOUBADO.json","graph_json":"https://pith.science/api/pith-number/SZQY77TQBVA3ARPWA7GDOUBADO/graph.json","events_json":"https://pith.science/api/pith-number/SZQY77TQBVA3ARPWA7GDOUBADO/events.json","paper":"https://pith.science/paper/SZQY77TQ"},"agent_actions":{"view_html":"https://pith.science/pith/SZQY77TQBVA3ARPWA7GDOUBADO","download_json":"https://pith.science/pith/SZQY77TQBVA3ARPWA7GDOUBADO.json","view_paper":"https://pith.science/paper/SZQY77TQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12824&json=true","fetch_graph":"https://pith.science/api/pith-number/SZQY77TQBVA3ARPWA7GDOUBADO/graph.json","fetch_events":"https://pith.science/api/pith-number/SZQY77TQBVA3ARPWA7GDOUBADO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZQY77TQBVA3ARPWA7GDOUBADO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZQY77TQBVA3ARPWA7GDOUBADO/action/storage_attestation","attest_author":"https://pith.science/pith/SZQY77TQBVA3ARPWA7GDOUBADO/action/author_attestation","sign_citation":"https://pith.science/pith/SZQY77TQBVA3ARPWA7GDOUBADO/action/citation_signature","submit_replication":"https://pith.science/pith/SZQY77TQBVA3ARPWA7GDOUBADO/action/replication_record"}},"created_at":"2026-07-05T10:47:35.519753+00:00","updated_at":"2026-07-05T10:47:35.519753+00:00"}