{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:KI7YEPOLZPETNPHKHXZFRS4HXG","short_pith_number":"pith:KI7YEPOL","schema_version":"1.0","canonical_sha256":"523f823dcbcbc936bcea3df258cb87b982579dfba60aca69db12b9ac9522bc6d","source":{"kind":"arxiv","id":"1612.00496","version":2},"attestation_state":"computed","paper":{"title":"3D Bounding Box Estimation Using Deep Learning and Geometry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arsalan Mousavian, Dragomir Anguelov, Jana Kosecka, John Flynn","submitted_at":"2016-12-01T22:16:48Z","abstract_excerpt":"We present a method for 3D object detection and pose estimation from a single image. In contrast to current techniques that only regress the 3D orientation of an object, our method first regresses relatively stable 3D object properties using a deep convolutional neural network and then combines these estimates with geometric constraints provided by a 2D object bounding box to produce a complete 3D bounding box. The first network output estimates the 3D object orientation using a novel hybrid discrete-continuous loss, which significantly outperforms the L2 loss. The second output regresses the "},"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":"1612.00496","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-01T22:16:48Z","cross_cats_sorted":[],"title_canon_sha256":"36285b33843b8091f59a3ebc38fc891c3da0dd948c8df2ed280b10d6f8478e4c","abstract_canon_sha256":"0b50851812a2aceadb088222c203057eb2228286aa7a51a8d7bf683fdb9f2da0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:38.713373Z","signature_b64":"eEbKeQUZCQLWg24FHx2Bla4v/bG6KNih0n9CpQX+05y2DWDLAnZdCBRb1hETOLlkIhJT5DR/jftnLnERW2bBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"523f823dcbcbc936bcea3df258cb87b982579dfba60aca69db12b9ac9522bc6d","last_reissued_at":"2026-05-18T00:46:38.712725Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:38.712725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Bounding Box Estimation Using Deep Learning and Geometry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arsalan Mousavian, Dragomir Anguelov, Jana Kosecka, John Flynn","submitted_at":"2016-12-01T22:16:48Z","abstract_excerpt":"We present a method for 3D object detection and pose estimation from a single image. In contrast to current techniques that only regress the 3D orientation of an object, our method first regresses relatively stable 3D object properties using a deep convolutional neural network and then combines these estimates with geometric constraints provided by a 2D object bounding box to produce a complete 3D bounding box. The first network output estimates the 3D object orientation using a novel hybrid discrete-continuous loss, which significantly outperforms the L2 loss. The second output regresses the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00496","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":""},"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":"1612.00496","created_at":"2026-05-18T00:46:38.712823+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.00496v2","created_at":"2026-05-18T00:46:38.712823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00496","created_at":"2026-05-18T00:46:38.712823+00:00"},{"alias_kind":"pith_short_12","alias_value":"KI7YEPOLZPET","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"KI7YEPOLZPETNPHK","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"KI7YEPOL","created_at":"2026-05-18T12:30:25.849896+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/KI7YEPOLZPETNPHKHXZFRS4HXG","json":"https://pith.science/pith/KI7YEPOLZPETNPHKHXZFRS4HXG.json","graph_json":"https://pith.science/api/pith-number/KI7YEPOLZPETNPHKHXZFRS4HXG/graph.json","events_json":"https://pith.science/api/pith-number/KI7YEPOLZPETNPHKHXZFRS4HXG/events.json","paper":"https://pith.science/paper/KI7YEPOL"},"agent_actions":{"view_html":"https://pith.science/pith/KI7YEPOLZPETNPHKHXZFRS4HXG","download_json":"https://pith.science/pith/KI7YEPOLZPETNPHKHXZFRS4HXG.json","view_paper":"https://pith.science/paper/KI7YEPOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.00496&json=true","fetch_graph":"https://pith.science/api/pith-number/KI7YEPOLZPETNPHKHXZFRS4HXG/graph.json","fetch_events":"https://pith.science/api/pith-number/KI7YEPOLZPETNPHKHXZFRS4HXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KI7YEPOLZPETNPHKHXZFRS4HXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KI7YEPOLZPETNPHKHXZFRS4HXG/action/storage_attestation","attest_author":"https://pith.science/pith/KI7YEPOLZPETNPHKHXZFRS4HXG/action/author_attestation","sign_citation":"https://pith.science/pith/KI7YEPOLZPETNPHKHXZFRS4HXG/action/citation_signature","submit_replication":"https://pith.science/pith/KI7YEPOLZPETNPHKHXZFRS4HXG/action/replication_record"}},"created_at":"2026-05-18T00:46:38.712823+00:00","updated_at":"2026-05-18T00:46:38.712823+00:00"}