{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Z2OVMKFFJ5O4LQCX53H5SR2NSK","short_pith_number":"pith:Z2OVMKFF","schema_version":"1.0","canonical_sha256":"ce9d5628a54f5dc5c057eecfd9474d928dd195236ea89b92e6694bcbbaa0cfa2","source":{"kind":"arxiv","id":"2204.03636","version":3},"attestation_state":"computed","paper":{"title":"SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guan Huang, Jie Zhou, Jiwen Lu, Linqing Zhao, Wenzhao Zheng, Yi Wei, Yongming Rao, Zheng Zhu","submitted_at":"2022-04-07T17:58:47Z","abstract_excerpt":"Depth estimation from images serves as the fundamental step of 3D perception for autonomous driving and is an economical alternative to expensive depth sensors like LiDAR. The temporal photometric constraints enables self-supervised depth estimation without labels, further facilitating its application. However, most existing methods predict the depth solely based on each monocular image and ignore the correlations among multiple surrounding cameras, which are typically available for modern self-driving vehicles. In this paper, we propose a SurroundDepth method to incorporate the information fr"},"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":"2204.03636","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-07T17:58:47Z","cross_cats_sorted":[],"title_canon_sha256":"2634ce7369a056009c493f807c4a05f032346dc5d3d9cfc564bafbdebe9695ac","abstract_canon_sha256":"ff497112338e7ca1a1d424299b91b9d5115625cf2844d11fb0e84c0e0fb1c3d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:59:21.273353Z","signature_b64":"m0Eeqa6DjMYgynjMUks/M3hxwAY5/naSR0Ikljg+NeoVSkpY5wp70LUhJANUHMa4JgmPK6tZIOy+TRdPIq62Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce9d5628a54f5dc5c057eecfd9474d928dd195236ea89b92e6694bcbbaa0cfa2","last_reissued_at":"2026-07-05T04:59:21.272859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:59:21.272859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guan Huang, Jie Zhou, Jiwen Lu, Linqing Zhao, Wenzhao Zheng, Yi Wei, Yongming Rao, Zheng Zhu","submitted_at":"2022-04-07T17:58:47Z","abstract_excerpt":"Depth estimation from images serves as the fundamental step of 3D perception for autonomous driving and is an economical alternative to expensive depth sensors like LiDAR. The temporal photometric constraints enables self-supervised depth estimation without labels, further facilitating its application. However, most existing methods predict the depth solely based on each monocular image and ignore the correlations among multiple surrounding cameras, which are typically available for modern self-driving vehicles. In this paper, we propose a SurroundDepth method to incorporate the information fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03636","kind":"arxiv","version":3},"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/2204.03636/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":"2204.03636","created_at":"2026-07-05T04:59:21.272915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03636v3","created_at":"2026-07-05T04:59:21.272915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03636","created_at":"2026-07-05T04:59:21.272915+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2OVMKFFJ5O4","created_at":"2026-07-05T04:59:21.272915+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2OVMKFFJ5O4LQCX","created_at":"2026-07-05T04:59:21.272915+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2OVMKFF","created_at":"2026-07-05T04:59:21.272915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20911","citing_title":"TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z2OVMKFFJ5O4LQCX53H5SR2NSK","json":"https://pith.science/pith/Z2OVMKFFJ5O4LQCX53H5SR2NSK.json","graph_json":"https://pith.science/api/pith-number/Z2OVMKFFJ5O4LQCX53H5SR2NSK/graph.json","events_json":"https://pith.science/api/pith-number/Z2OVMKFFJ5O4LQCX53H5SR2NSK/events.json","paper":"https://pith.science/paper/Z2OVMKFF"},"agent_actions":{"view_html":"https://pith.science/pith/Z2OVMKFFJ5O4LQCX53H5SR2NSK","download_json":"https://pith.science/pith/Z2OVMKFFJ5O4LQCX53H5SR2NSK.json","view_paper":"https://pith.science/paper/Z2OVMKFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03636&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2OVMKFFJ5O4LQCX53H5SR2NSK/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2OVMKFFJ5O4LQCX53H5SR2NSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2OVMKFFJ5O4LQCX53H5SR2NSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2OVMKFFJ5O4LQCX53H5SR2NSK/action/storage_attestation","attest_author":"https://pith.science/pith/Z2OVMKFFJ5O4LQCX53H5SR2NSK/action/author_attestation","sign_citation":"https://pith.science/pith/Z2OVMKFFJ5O4LQCX53H5SR2NSK/action/citation_signature","submit_replication":"https://pith.science/pith/Z2OVMKFFJ5O4LQCX53H5SR2NSK/action/replication_record"}},"created_at":"2026-07-05T04:59:21.272915+00:00","updated_at":"2026-07-05T04:59:21.272915+00:00"}