{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EQFLYODOX2Y4X2Y637YRHV5WAM","short_pith_number":"pith:EQFLYODO","schema_version":"1.0","canonical_sha256":"240abc386ebeb1cbeb1edff113d7b6033179dce09ba85f0464e21e2e20ad8798","source":{"kind":"arxiv","id":"2410.02924","version":2},"attestation_state":"computed","paper":{"title":"RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Wong, Byung-Woo Hong, Daniel Wang, Dong Lao, Fengyu Yang, Hyoungseob Park, Stefano Soatto, Yangchao Wu, Ziyao Zeng","submitted_at":"2024-10-03T19:18:13Z","abstract_excerpt":"We propose a method for metric-scale monocular depth estimation. Inferring depth from a single image is an ill-posed problem due to the loss of scale from perspective projection during the image formation process. Any scale chosen is a bias, typically stemming from training on a dataset; hence, existing works have instead opted to use relative (normalized, inverse) depth. Our goal is to recover metric-scaled depth maps through a linear transformation. The crux of our method lies in the observation that certain objects (e.g., cars, trees, street signs) are typically found or associated with cer"},"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":"2410.02924","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T19:18:13Z","cross_cats_sorted":[],"title_canon_sha256":"852141752e986bb5f9a8f5e84e963cf46ad06b6ef96c1c185dd7e578bc1ee3d1","abstract_canon_sha256":"f76e6aa6b469a6994c6b14076b7ce43740aed57d14d7287181addd0f2829b30d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:21.794012Z","signature_b64":"DVtafy9x5GXcqYHpKyBVN1o1qwxqnWQiXvQaoAuGvVCLr0T9OICWiL2RLj44f+7j+vPeJt0ZrgUzOQ5abu5BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"240abc386ebeb1cbeb1edff113d7b6033179dce09ba85f0464e21e2e20ad8798","last_reissued_at":"2026-07-05T09:30:21.793631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:21.793631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Wong, Byung-Woo Hong, Daniel Wang, Dong Lao, Fengyu Yang, Hyoungseob Park, Stefano Soatto, Yangchao Wu, Ziyao Zeng","submitted_at":"2024-10-03T19:18:13Z","abstract_excerpt":"We propose a method for metric-scale monocular depth estimation. Inferring depth from a single image is an ill-posed problem due to the loss of scale from perspective projection during the image formation process. Any scale chosen is a bias, typically stemming from training on a dataset; hence, existing works have instead opted to use relative (normalized, inverse) depth. Our goal is to recover metric-scaled depth maps through a linear transformation. The crux of our method lies in the observation that certain objects (e.g., cars, trees, street signs) are typically found or associated with cer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02924","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/2410.02924/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":"2410.02924","created_at":"2026-07-05T09:30:21.793687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02924v2","created_at":"2026-07-05T09:30:21.793687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02924","created_at":"2026-07-05T09:30:21.793687+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQFLYODOX2Y4","created_at":"2026-07-05T09:30:21.793687+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQFLYODOX2Y4X2Y6","created_at":"2026-07-05T09:30:21.793687+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQFLYODO","created_at":"2026-07-05T09:30:21.793687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06779","citing_title":"URS-Stereo: Uncertainty-Guided Residual Search for Real-Time Stereo Matching","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10588","citing_title":"Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00072","citing_title":"XekRung Technical Report","ref_index":124,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQFLYODOX2Y4X2Y637YRHV5WAM","json":"https://pith.science/pith/EQFLYODOX2Y4X2Y637YRHV5WAM.json","graph_json":"https://pith.science/api/pith-number/EQFLYODOX2Y4X2Y637YRHV5WAM/graph.json","events_json":"https://pith.science/api/pith-number/EQFLYODOX2Y4X2Y637YRHV5WAM/events.json","paper":"https://pith.science/paper/EQFLYODO"},"agent_actions":{"view_html":"https://pith.science/pith/EQFLYODOX2Y4X2Y637YRHV5WAM","download_json":"https://pith.science/pith/EQFLYODOX2Y4X2Y637YRHV5WAM.json","view_paper":"https://pith.science/paper/EQFLYODO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02924&json=true","fetch_graph":"https://pith.science/api/pith-number/EQFLYODOX2Y4X2Y637YRHV5WAM/graph.json","fetch_events":"https://pith.science/api/pith-number/EQFLYODOX2Y4X2Y637YRHV5WAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQFLYODOX2Y4X2Y637YRHV5WAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQFLYODOX2Y4X2Y637YRHV5WAM/action/storage_attestation","attest_author":"https://pith.science/pith/EQFLYODOX2Y4X2Y637YRHV5WAM/action/author_attestation","sign_citation":"https://pith.science/pith/EQFLYODOX2Y4X2Y637YRHV5WAM/action/citation_signature","submit_replication":"https://pith.science/pith/EQFLYODOX2Y4X2Y637YRHV5WAM/action/replication_record"}},"created_at":"2026-07-05T09:30:21.793687+00:00","updated_at":"2026-07-05T09:30:21.793687+00:00"}