{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UIKTFFJELR5I6QTDZWJFO522R4","short_pith_number":"pith:UIKTFFJE","schema_version":"1.0","canonical_sha256":"a2153295245c7a8f4263cd9257775a8f2e9abd0782f52efb701d28d2a5fe030d","source":{"kind":"arxiv","id":"1905.02693","version":4},"attestation_state":"computed","paper":{"title":"3D Packing for Self-Supervised Monocular Depth Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Adrien Gaidon, Allan Raventos, Rares Ambrus, Sudeep Pillai, Vitor Guizilini","submitted_at":"2019-05-06T17:09:52Z","abstract_excerpt":"Although cameras are ubiquitous, robotic platforms typically rely on active sensors like LiDAR for direct 3D perception. In this work, we propose a novel self-supervised monocular depth estimation method combining geometry with a new deep network, PackNet, learned only from unlabeled monocular videos. Our architecture leverages novel symmetrical packing and unpacking blocks to jointly learn to compress and decompress detail-preserving representations using 3D convolutions. Although self-supervised, our method outperforms other self, semi, and fully supervised methods on the KITTI benchmark. Th"},"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":"1905.02693","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-06T17:09:52Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"3a8fa0a4d6c70496f8da53b6f0e0693a1ffc1e84ccf548e02ff6f6c74b6de4c2","abstract_canon_sha256":"8b9ed505f99b742a6833e3d162636e22183705dc29573e846aea9ecb6dd74d8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:02.331811Z","signature_b64":"lS8eHw9LXeRW9kvLPe/ToKsFojmGSAEokeJZvOAGl5KZZagNbIPdEK60qEp2CbMnQfvrQijaPp4vaH9z3t+ICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2153295245c7a8f4263cd9257775a8f2e9abd0782f52efb701d28d2a5fe030d","last_reissued_at":"2026-07-05T00:51:02.331415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:02.331415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Packing for Self-Supervised Monocular Depth Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Adrien Gaidon, Allan Raventos, Rares Ambrus, Sudeep Pillai, Vitor Guizilini","submitted_at":"2019-05-06T17:09:52Z","abstract_excerpt":"Although cameras are ubiquitous, robotic platforms typically rely on active sensors like LiDAR for direct 3D perception. In this work, we propose a novel self-supervised monocular depth estimation method combining geometry with a new deep network, PackNet, learned only from unlabeled monocular videos. Our architecture leverages novel symmetrical packing and unpacking blocks to jointly learn to compress and decompress detail-preserving representations using 3D convolutions. Although self-supervised, our method outperforms other self, semi, and fully supervised methods on the KITTI benchmark. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02693","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.02693/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":"1905.02693","created_at":"2026-07-05T00:51:02.331471+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.02693v4","created_at":"2026-07-05T00:51:02.331471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02693","created_at":"2026-07-05T00:51:02.331471+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIKTFFJELR5I","created_at":"2026-07-05T00:51:02.331471+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIKTFFJELR5I6QTD","created_at":"2026-07-05T00:51:02.331471+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIKTFFJE","created_at":"2026-07-05T00:51:02.331471+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/UIKTFFJELR5I6QTDZWJFO522R4","json":"https://pith.science/pith/UIKTFFJELR5I6QTDZWJFO522R4.json","graph_json":"https://pith.science/api/pith-number/UIKTFFJELR5I6QTDZWJFO522R4/graph.json","events_json":"https://pith.science/api/pith-number/UIKTFFJELR5I6QTDZWJFO522R4/events.json","paper":"https://pith.science/paper/UIKTFFJE"},"agent_actions":{"view_html":"https://pith.science/pith/UIKTFFJELR5I6QTDZWJFO522R4","download_json":"https://pith.science/pith/UIKTFFJELR5I6QTDZWJFO522R4.json","view_paper":"https://pith.science/paper/UIKTFFJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.02693&json=true","fetch_graph":"https://pith.science/api/pith-number/UIKTFFJELR5I6QTDZWJFO522R4/graph.json","fetch_events":"https://pith.science/api/pith-number/UIKTFFJELR5I6QTDZWJFO522R4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIKTFFJELR5I6QTDZWJFO522R4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIKTFFJELR5I6QTDZWJFO522R4/action/storage_attestation","attest_author":"https://pith.science/pith/UIKTFFJELR5I6QTDZWJFO522R4/action/author_attestation","sign_citation":"https://pith.science/pith/UIKTFFJELR5I6QTDZWJFO522R4/action/citation_signature","submit_replication":"https://pith.science/pith/UIKTFFJELR5I6QTDZWJFO522R4/action/replication_record"}},"created_at":"2026-07-05T00:51:02.331471+00:00","updated_at":"2026-07-05T00:51:02.331471+00:00"}