{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VA4OGPIKWQA3ZCEVXSFFUUPKZQ","short_pith_number":"pith:VA4OGPIK","schema_version":"1.0","canonical_sha256":"a838e33d0ab401bc8895bc8a5a51eacc3a863da7950f9809c018646fe3afac6c","source":{"kind":"arxiv","id":"2403.11270","version":2},"attestation_state":"computed","paper":{"title":"Bilateral Propagation Network for Depth Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boshi An, Fei-Peng Tian, Jian Li, Jie Tang, Ping Tan","submitted_at":"2024-03-17T16:48:46Z","abstract_excerpt":"Depth completion aims to derive a dense depth map from sparse depth measurements with a synchronized color image. Current state-of-the-art (SOTA) methods are predominantly propagation-based, which work as an iterative refinement on the initial estimated dense depth. However, the initial depth estimations mostly result from direct applications of convolutional layers on the sparse depth map. In this paper, we present a Bilateral Propagation Network (BP-Net), that propagates depth at the earliest stage to avoid directly convolving on sparse data. Specifically, our approach propagates the target "},"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":"2403.11270","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T16:48:46Z","cross_cats_sorted":[],"title_canon_sha256":"8fe6bded0e1670ee79fad3b305e84c3bb298cc9bdd6cb4f00e3cf0d4a47d948a","abstract_canon_sha256":"b045d2039b28d44efee1ef2a98a23f0c2e554d479412d09eb827d2c79143fd3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:52.022542Z","signature_b64":"z1YwO3YEy7t8n3fRnwAJ9tn477uj2aNw1lNDhLYwrh/SlBQkjgbmq2WumJGyaz5qw/PRYzTHR1GH7eVULzekCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a838e33d0ab401bc8895bc8a5a51eacc3a863da7950f9809c018646fe3afac6c","last_reissued_at":"2026-07-05T08:02:52.022055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:52.022055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bilateral Propagation Network for Depth Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boshi An, Fei-Peng Tian, Jian Li, Jie Tang, Ping Tan","submitted_at":"2024-03-17T16:48:46Z","abstract_excerpt":"Depth completion aims to derive a dense depth map from sparse depth measurements with a synchronized color image. Current state-of-the-art (SOTA) methods are predominantly propagation-based, which work as an iterative refinement on the initial estimated dense depth. However, the initial depth estimations mostly result from direct applications of convolutional layers on the sparse depth map. In this paper, we present a Bilateral Propagation Network (BP-Net), that propagates depth at the earliest stage to avoid directly convolving on sparse data. Specifically, our approach propagates the target "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11270","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/2403.11270/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":"2403.11270","created_at":"2026-07-05T08:02:52.022112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11270v2","created_at":"2026-07-05T08:02:52.022112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11270","created_at":"2026-07-05T08:02:52.022112+00:00"},{"alias_kind":"pith_short_12","alias_value":"VA4OGPIKWQA3","created_at":"2026-07-05T08:02:52.022112+00:00"},{"alias_kind":"pith_short_16","alias_value":"VA4OGPIKWQA3ZCEV","created_at":"2026-07-05T08:02:52.022112+00:00"},{"alias_kind":"pith_short_8","alias_value":"VA4OGPIK","created_at":"2026-07-05T08:02:52.022112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18790","citing_title":"EfficientPENet: Real-Time Depth Completion from Sparse LiDAR via Lightweight Multi-Modal Fusion","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VA4OGPIKWQA3ZCEVXSFFUUPKZQ","json":"https://pith.science/pith/VA4OGPIKWQA3ZCEVXSFFUUPKZQ.json","graph_json":"https://pith.science/api/pith-number/VA4OGPIKWQA3ZCEVXSFFUUPKZQ/graph.json","events_json":"https://pith.science/api/pith-number/VA4OGPIKWQA3ZCEVXSFFUUPKZQ/events.json","paper":"https://pith.science/paper/VA4OGPIK"},"agent_actions":{"view_html":"https://pith.science/pith/VA4OGPIKWQA3ZCEVXSFFUUPKZQ","download_json":"https://pith.science/pith/VA4OGPIKWQA3ZCEVXSFFUUPKZQ.json","view_paper":"https://pith.science/paper/VA4OGPIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11270&json=true","fetch_graph":"https://pith.science/api/pith-number/VA4OGPIKWQA3ZCEVXSFFUUPKZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VA4OGPIKWQA3ZCEVXSFFUUPKZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VA4OGPIKWQA3ZCEVXSFFUUPKZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VA4OGPIKWQA3ZCEVXSFFUUPKZQ/action/storage_attestation","attest_author":"https://pith.science/pith/VA4OGPIKWQA3ZCEVXSFFUUPKZQ/action/author_attestation","sign_citation":"https://pith.science/pith/VA4OGPIKWQA3ZCEVXSFFUUPKZQ/action/citation_signature","submit_replication":"https://pith.science/pith/VA4OGPIKWQA3ZCEVXSFFUUPKZQ/action/replication_record"}},"created_at":"2026-07-05T08:02:52.022112+00:00","updated_at":"2026-07-05T08:02:52.022112+00:00"}