{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:SWTX4E65HZAKCUQX2PFNNO657I","short_pith_number":"pith:SWTX4E65","schema_version":"1.0","canonical_sha256":"95a77e13dd3e40a15217d3cad6bbddfa047ddbde3a8d6677ccae5dc45d5c062d","source":{"kind":"arxiv","id":"1607.00730","version":4},"attestation_state":"computed","paper":{"title":"A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Jun Li, Reinhard Klein","submitted_at":"2016-07-04T03:22:45Z","abstract_excerpt":"Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem. State-of-the-art deep learning methods can now estimate accurate 2D depth maps, but when the maps are projected into 3D, they lack local detail and are often highly distorted. We propose a fast-to-train two-streamed CNN that predicts depth and depth gradients, which are then fused together into an accurate and detailed depth map. We also define a novel set loss over multiple images; by regularizing the estimation between a common set of images, the network is less prone to over-fitting and achieves bette"},"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":"1607.00730","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-07-04T03:22:45Z","cross_cats_sorted":[],"title_canon_sha256":"fe0e768cf48878eecb7043f8370d75879d15d82ab91f92a654353b6e4152aed5","abstract_canon_sha256":"42f38acbe0f4f2dc70bc82fc09b2d265799e087c4c91a6599f529d1d38d26c49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:01.928033Z","signature_b64":"wtg+/pykS7D9F3QCuSp6GoR39yT9hcDccMFzQMOZoHK6jzP1AyndyhQjjl6wNSLh+ZI4kgF0tRiUjqP2h/l2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95a77e13dd3e40a15217d3cad6bbddfa047ddbde3a8d6677ccae5dc45d5c062d","last_reissued_at":"2026-05-18T00:29:01.926724Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:01.926724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Two-Streamed Network for Estimating Fine-Scaled Depth Maps from Single RGB Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Jun Li, Reinhard Klein","submitted_at":"2016-07-04T03:22:45Z","abstract_excerpt":"Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem. State-of-the-art deep learning methods can now estimate accurate 2D depth maps, but when the maps are projected into 3D, they lack local detail and are often highly distorted. We propose a fast-to-train two-streamed CNN that predicts depth and depth gradients, which are then fused together into an accurate and detailed depth map. We also define a novel set loss over multiple images; by regularizing the estimation between a common set of images, the network is less prone to over-fitting and achieves bette"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.00730","kind":"arxiv","version":4},"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":"1607.00730","created_at":"2026-05-18T00:29:01.927040+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.00730v4","created_at":"2026-05-18T00:29:01.927040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.00730","created_at":"2026-05-18T00:29:01.927040+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWTX4E65HZAK","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWTX4E65HZAKCUQX","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWTX4E65","created_at":"2026-05-18T12:30:44.179134+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/SWTX4E65HZAKCUQX2PFNNO657I","json":"https://pith.science/pith/SWTX4E65HZAKCUQX2PFNNO657I.json","graph_json":"https://pith.science/api/pith-number/SWTX4E65HZAKCUQX2PFNNO657I/graph.json","events_json":"https://pith.science/api/pith-number/SWTX4E65HZAKCUQX2PFNNO657I/events.json","paper":"https://pith.science/paper/SWTX4E65"},"agent_actions":{"view_html":"https://pith.science/pith/SWTX4E65HZAKCUQX2PFNNO657I","download_json":"https://pith.science/pith/SWTX4E65HZAKCUQX2PFNNO657I.json","view_paper":"https://pith.science/paper/SWTX4E65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.00730&json=true","fetch_graph":"https://pith.science/api/pith-number/SWTX4E65HZAKCUQX2PFNNO657I/graph.json","fetch_events":"https://pith.science/api/pith-number/SWTX4E65HZAKCUQX2PFNNO657I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWTX4E65HZAKCUQX2PFNNO657I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWTX4E65HZAKCUQX2PFNNO657I/action/storage_attestation","attest_author":"https://pith.science/pith/SWTX4E65HZAKCUQX2PFNNO657I/action/author_attestation","sign_citation":"https://pith.science/pith/SWTX4E65HZAKCUQX2PFNNO657I/action/citation_signature","submit_replication":"https://pith.science/pith/SWTX4E65HZAKCUQX2PFNNO657I/action/replication_record"}},"created_at":"2026-05-18T00:29:01.927040+00:00","updated_at":"2026-05-18T00:29:01.927040+00:00"}