{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BBITNM3Q4UUVIG4WQMKMSN3BDZ","short_pith_number":"pith:BBITNM3Q","schema_version":"1.0","canonical_sha256":"085136b370e529541b968314c937611e6b28b9ffb44b95f69a9cc813ffd90cd6","source":{"kind":"arxiv","id":"2311.04391","version":1},"attestation_state":"computed","paper":{"title":"3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenfeng Xu, Huan Ling, Or Litany, Sanja Fidler","submitted_at":"2023-11-07T23:46:41Z","abstract_excerpt":"We present 3DiffTection, a state-of-the-art method for 3D object detection from single images, leveraging features from a 3D-aware diffusion model. Annotating large-scale image data for 3D detection is resource-intensive and time-consuming. Recently, pretrained large image diffusion models have become prominent as effective feature extractors for 2D perception tasks. However, these features are initially trained on paired text and image data, which are not optimized for 3D tasks, and often exhibit a domain gap when applied to the target data. Our approach bridges these gaps through two special"},"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":"2311.04391","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T23:46:41Z","cross_cats_sorted":[],"title_canon_sha256":"adaf4bd17c89dd847742694d9ca1c69f300d0cf80a45f9c8e5021b971bf03fea","abstract_canon_sha256":"c948ea2b6deb461108f0f45820d7d05be7fb0a711826f47916d7da95b9de6666"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:34.838997Z","signature_b64":"bwAnRKlQ5pKefctfPDMXdHTrrt49ltuzzHzfaqCAJHHP09kg+WzJeHw1ovAowK81SAIrkyBzdYFhY/2LlsL6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"085136b370e529541b968314c937611e6b28b9ffb44b95f69a9cc813ffd90cd6","last_reissued_at":"2026-07-05T07:10:34.838539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:34.838539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenfeng Xu, Huan Ling, Or Litany, Sanja Fidler","submitted_at":"2023-11-07T23:46:41Z","abstract_excerpt":"We present 3DiffTection, a state-of-the-art method for 3D object detection from single images, leveraging features from a 3D-aware diffusion model. Annotating large-scale image data for 3D detection is resource-intensive and time-consuming. Recently, pretrained large image diffusion models have become prominent as effective feature extractors for 2D perception tasks. However, these features are initially trained on paired text and image data, which are not optimized for 3D tasks, and often exhibit a domain gap when applied to the target data. Our approach bridges these gaps through two special"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04391","kind":"arxiv","version":1},"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/2311.04391/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":"2311.04391","created_at":"2026-07-05T07:10:34.838603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04391v1","created_at":"2026-07-05T07:10:34.838603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04391","created_at":"2026-07-05T07:10:34.838603+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBITNM3Q4UUV","created_at":"2026-07-05T07:10:34.838603+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBITNM3Q4UUVIG4W","created_at":"2026-07-05T07:10:34.838603+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBITNM3Q","created_at":"2026-07-05T07:10:34.838603+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/BBITNM3Q4UUVIG4WQMKMSN3BDZ","json":"https://pith.science/pith/BBITNM3Q4UUVIG4WQMKMSN3BDZ.json","graph_json":"https://pith.science/api/pith-number/BBITNM3Q4UUVIG4WQMKMSN3BDZ/graph.json","events_json":"https://pith.science/api/pith-number/BBITNM3Q4UUVIG4WQMKMSN3BDZ/events.json","paper":"https://pith.science/paper/BBITNM3Q"},"agent_actions":{"view_html":"https://pith.science/pith/BBITNM3Q4UUVIG4WQMKMSN3BDZ","download_json":"https://pith.science/pith/BBITNM3Q4UUVIG4WQMKMSN3BDZ.json","view_paper":"https://pith.science/paper/BBITNM3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04391&json=true","fetch_graph":"https://pith.science/api/pith-number/BBITNM3Q4UUVIG4WQMKMSN3BDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/BBITNM3Q4UUVIG4WQMKMSN3BDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBITNM3Q4UUVIG4WQMKMSN3BDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBITNM3Q4UUVIG4WQMKMSN3BDZ/action/storage_attestation","attest_author":"https://pith.science/pith/BBITNM3Q4UUVIG4WQMKMSN3BDZ/action/author_attestation","sign_citation":"https://pith.science/pith/BBITNM3Q4UUVIG4WQMKMSN3BDZ/action/citation_signature","submit_replication":"https://pith.science/pith/BBITNM3Q4UUVIG4WQMKMSN3BDZ/action/replication_record"}},"created_at":"2026-07-05T07:10:34.838603+00:00","updated_at":"2026-07-05T07:10:34.838603+00:00"}