{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DTMUIQRS46JF75ASJ7NR52BK6C","short_pith_number":"pith:DTMUIQRS","schema_version":"1.0","canonical_sha256":"1cd9444232e7925ff4124fdb1ee82af081250ae5f366abc1c1ccd0a4afa913c5","source":{"kind":"arxiv","id":"2502.19204","version":2},"attestation_state":"computed","paper":{"title":"Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Zhang, Dongyan Guo, Hongji Li, Ruibo Li, Xiankang He, Ying Cui","submitted_at":"2025-02-26T15:10:05Z","abstract_excerpt":"Recent advances in zero-shot monocular depth estimation(MDE) have significantly improved generalization by unifying depth distributions through normalized depth representations and by leveraging large-scale unlabeled data via pseudo-label distillation. However, existing methods that rely on global depth normalization treat all depth values equally, which can amplify noise in pseudo-labels and reduce distillation effectiveness. In this paper, we present a systematic analysis of depth normalization strategies in the context of pseudo-label distillation. Our study shows that, under recent distill"},"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":"2502.19204","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-26T15:10:05Z","cross_cats_sorted":[],"title_canon_sha256":"b4716be9c4d2122a477bc3a837f7564898595df9539fb6e67a02a0ba4333dfc3","abstract_canon_sha256":"23ba8ad73d8850bd170a09cf1f6bbd36e5fabf503566a7883b13135fc736d60b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:33.885282Z","signature_b64":"dfqLa5PWvpmyIqN+ErsmV9gHt+2YHe7PkJOge7ajwLf4euaVZ7DlSugMya3TeYoI84R73bAblQ6BQF5W0d7RCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cd9444232e7925ff4124fdb1ee82af081250ae5f366abc1c1ccd0a4afa913c5","last_reissued_at":"2026-07-05T10:51:33.884736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:33.884736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi Zhang, Dongyan Guo, Hongji Li, Ruibo Li, Xiankang He, Ying Cui","submitted_at":"2025-02-26T15:10:05Z","abstract_excerpt":"Recent advances in zero-shot monocular depth estimation(MDE) have significantly improved generalization by unifying depth distributions through normalized depth representations and by leveraging large-scale unlabeled data via pseudo-label distillation. However, existing methods that rely on global depth normalization treat all depth values equally, which can amplify noise in pseudo-labels and reduce distillation effectiveness. In this paper, we present a systematic analysis of depth normalization strategies in the context of pseudo-label distillation. Our study shows that, under recent distill"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19204","kind":"arxiv","version":2},"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/2502.19204/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":"2502.19204","created_at":"2026-07-05T10:51:33.884797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.19204v2","created_at":"2026-07-05T10:51:33.884797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19204","created_at":"2026-07-05T10:51:33.884797+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTMUIQRS46JF","created_at":"2026-07-05T10:51:33.884797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTMUIQRS46JF75AS","created_at":"2026-07-05T10:51:33.884797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTMUIQRS","created_at":"2026-07-05T10:51:33.884797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24893","citing_title":"BED-SAM2: Boundary-Enhanced-Depth SAM2 via Monocular Geometric Priors","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02935","citing_title":"Modality-Specific Hierarchical Enhancement for RGB-D Camouflaged Object Detection","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24328","citing_title":"Monocular Depth Estimation via Neural Network with Learnable Algebraic Group and Ring Structures","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DTMUIQRS46JF75ASJ7NR52BK6C","json":"https://pith.science/pith/DTMUIQRS46JF75ASJ7NR52BK6C.json","graph_json":"https://pith.science/api/pith-number/DTMUIQRS46JF75ASJ7NR52BK6C/graph.json","events_json":"https://pith.science/api/pith-number/DTMUIQRS46JF75ASJ7NR52BK6C/events.json","paper":"https://pith.science/paper/DTMUIQRS"},"agent_actions":{"view_html":"https://pith.science/pith/DTMUIQRS46JF75ASJ7NR52BK6C","download_json":"https://pith.science/pith/DTMUIQRS46JF75ASJ7NR52BK6C.json","view_paper":"https://pith.science/paper/DTMUIQRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.19204&json=true","fetch_graph":"https://pith.science/api/pith-number/DTMUIQRS46JF75ASJ7NR52BK6C/graph.json","fetch_events":"https://pith.science/api/pith-number/DTMUIQRS46JF75ASJ7NR52BK6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTMUIQRS46JF75ASJ7NR52BK6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTMUIQRS46JF75ASJ7NR52BK6C/action/storage_attestation","attest_author":"https://pith.science/pith/DTMUIQRS46JF75ASJ7NR52BK6C/action/author_attestation","sign_citation":"https://pith.science/pith/DTMUIQRS46JF75ASJ7NR52BK6C/action/citation_signature","submit_replication":"https://pith.science/pith/DTMUIQRS46JF75ASJ7NR52BK6C/action/replication_record"}},"created_at":"2026-07-05T10:51:33.884797+00:00","updated_at":"2026-07-05T10:51:33.884797+00:00"}