{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GBBK2YH4O2FRZEE2C52YVPRCDV","short_pith_number":"pith:GBBK2YH4","schema_version":"1.0","canonical_sha256":"3042ad60fc768b1c909a17758abe221d413f17e00893f292a3350cea3224dabc","source":{"kind":"arxiv","id":"2207.10660","version":2},"attestation_state":"computed","paper":{"title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Kumar, Garrick Brazil, Georgia Gkioxari, Julian Straub, Justin Johnson, Nikhila Ravi","submitted_at":"2022-07-21T17:56:22Z","abstract_excerpt":"Recognizing scenes and objects in 3D from a single image is a longstanding goal of computer vision with applications in robotics and AR/VR. For 2D recognition, large datasets and scalable solutions have led to unprecedented advances. In 3D, existing benchmarks are small in size and approaches specialize in few object categories and specific domains, e.g. urban driving scenes. Motivated by the success of 2D recognition, we revisit the task of 3D object detection by introducing a large benchmark, called Omni3D. Omni3D re-purposes and combines existing datasets resulting in 234k images annotated "},"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":"2207.10660","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-21T17:56:22Z","cross_cats_sorted":[],"title_canon_sha256":"031f4f68c43345171c5ee6c9a3d42907f55e7a1c45cf710f44891d1f1d25203b","abstract_canon_sha256":"c2debb28991e95beb3ea7d4c24b20258a90c3add79446481f2b909b408c7a7f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:12.195712Z","signature_b64":"/gKAjZP4h+Zw5ulvrrvmenaf3UOdwz+q+Fp0OF8qW6gG+7JJ/ZcoGBD+xAxVCVGorAE7vr/AHCqWfayb+/xaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3042ad60fc768b1c909a17758abe221d413f17e00893f292a3350cea3224dabc","last_reissued_at":"2026-07-05T05:54:12.195150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:12.195150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Kumar, Garrick Brazil, Georgia Gkioxari, Julian Straub, Justin Johnson, Nikhila Ravi","submitted_at":"2022-07-21T17:56:22Z","abstract_excerpt":"Recognizing scenes and objects in 3D from a single image is a longstanding goal of computer vision with applications in robotics and AR/VR. For 2D recognition, large datasets and scalable solutions have led to unprecedented advances. In 3D, existing benchmarks are small in size and approaches specialize in few object categories and specific domains, e.g. urban driving scenes. Motivated by the success of 2D recognition, we revisit the task of 3D object detection by introducing a large benchmark, called Omni3D. Omni3D re-purposes and combines existing datasets resulting in 234k images annotated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10660","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/2207.10660/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":"2207.10660","created_at":"2026-07-05T05:54:12.195208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.10660v2","created_at":"2026-07-05T05:54:12.195208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10660","created_at":"2026-07-05T05:54:12.195208+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBBK2YH4O2FR","created_at":"2026-07-05T05:54:12.195208+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBBK2YH4O2FRZEE2","created_at":"2026-07-05T05:54:12.195208+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBBK2YH4","created_at":"2026-07-05T05:54:12.195208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17539","citing_title":"Reinforcing Dual-Path Reasoning in Spatial Vision Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08626","citing_title":"WildDet3D: Scaling Promptable 3D Detection in the Wild","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GBBK2YH4O2FRZEE2C52YVPRCDV","json":"https://pith.science/pith/GBBK2YH4O2FRZEE2C52YVPRCDV.json","graph_json":"https://pith.science/api/pith-number/GBBK2YH4O2FRZEE2C52YVPRCDV/graph.json","events_json":"https://pith.science/api/pith-number/GBBK2YH4O2FRZEE2C52YVPRCDV/events.json","paper":"https://pith.science/paper/GBBK2YH4"},"agent_actions":{"view_html":"https://pith.science/pith/GBBK2YH4O2FRZEE2C52YVPRCDV","download_json":"https://pith.science/pith/GBBK2YH4O2FRZEE2C52YVPRCDV.json","view_paper":"https://pith.science/paper/GBBK2YH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.10660&json=true","fetch_graph":"https://pith.science/api/pith-number/GBBK2YH4O2FRZEE2C52YVPRCDV/graph.json","fetch_events":"https://pith.science/api/pith-number/GBBK2YH4O2FRZEE2C52YVPRCDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBBK2YH4O2FRZEE2C52YVPRCDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBBK2YH4O2FRZEE2C52YVPRCDV/action/storage_attestation","attest_author":"https://pith.science/pith/GBBK2YH4O2FRZEE2C52YVPRCDV/action/author_attestation","sign_citation":"https://pith.science/pith/GBBK2YH4O2FRZEE2C52YVPRCDV/action/citation_signature","submit_replication":"https://pith.science/pith/GBBK2YH4O2FRZEE2C52YVPRCDV/action/replication_record"}},"created_at":"2026-07-05T05:54:12.195208+00:00","updated_at":"2026-07-05T05:54:12.195208+00:00"}