{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NTVJ7MBGJPIHMY5TUHSJ22DROG","short_pith_number":"pith:NTVJ7MBG","schema_version":"1.0","canonical_sha256":"6cea9fb0264bd07663b3a1e49d687171aeaaf1c53ca2304a85bcb4c9c5244e1c","source":{"kind":"arxiv","id":"2504.13580","version":4},"attestation_state":"computed","paper":{"title":"Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Friedrich Fraundorfer, Sinisa Stekovic, Stefan Ainetter, Vincent Lepetit, Yuchen Rao","submitted_at":"2025-04-18T09:33:45Z","abstract_excerpt":"High-level 3D scene understanding is essential in many applications. However, the challenges of generating accurate 3D annotations make development of deep learning models difficult. We turn to recent advancements in automatic retrieval of synthetic CAD models, and show that data generated by such methods can be used as high-quality ground truth for training supervised deep learning models. More exactly, we employ a pipeline akin to the one previously used to automatically annotate objects in ScanNet scenes with their 9D poses and CAD models. This time, we apply it to the recent ScanNet++ v1 d"},"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":"2504.13580","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-18T09:33:45Z","cross_cats_sorted":[],"title_canon_sha256":"b5a835da8967102139bd7168335e80a683fcdc591b79752db532a836167ebc06","abstract_canon_sha256":"b6119ee40f55ba0f28f3585eb1a6f043eddc6b64b2000379ff156b8f5227c29c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:59.277239Z","signature_b64":"IFEuiFjDZJHOcDLAc+AcD7V0QygHZDGKaW0hykbS25lvgS+1y7h7KvnRh9XmBbRjw+5AXQXaxC8bLSpMmzO6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cea9fb0264bd07663b3a1e49d687171aeaaf1c53ca2304a85bcb4c9c5244e1c","last_reissued_at":"2026-07-05T11:03:59.276740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:59.276740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Friedrich Fraundorfer, Sinisa Stekovic, Stefan Ainetter, Vincent Lepetit, Yuchen Rao","submitted_at":"2025-04-18T09:33:45Z","abstract_excerpt":"High-level 3D scene understanding is essential in many applications. However, the challenges of generating accurate 3D annotations make development of deep learning models difficult. We turn to recent advancements in automatic retrieval of synthetic CAD models, and show that data generated by such methods can be used as high-quality ground truth for training supervised deep learning models. More exactly, we employ a pipeline akin to the one previously used to automatically annotate objects in ScanNet scenes with their 9D poses and CAD models. This time, we apply it to the recent ScanNet++ v1 d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13580","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/2504.13580/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":"2504.13580","created_at":"2026-07-05T11:03:59.276798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13580v4","created_at":"2026-07-05T11:03:59.276798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13580","created_at":"2026-07-05T11:03:59.276798+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTVJ7MBGJPIH","created_at":"2026-07-05T11:03:59.276798+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTVJ7MBGJPIHMY5T","created_at":"2026-07-05T11:03:59.276798+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTVJ7MBG","created_at":"2026-07-05T11:03:59.276798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19019","citing_title":"FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTVJ7MBGJPIHMY5TUHSJ22DROG","json":"https://pith.science/pith/NTVJ7MBGJPIHMY5TUHSJ22DROG.json","graph_json":"https://pith.science/api/pith-number/NTVJ7MBGJPIHMY5TUHSJ22DROG/graph.json","events_json":"https://pith.science/api/pith-number/NTVJ7MBGJPIHMY5TUHSJ22DROG/events.json","paper":"https://pith.science/paper/NTVJ7MBG"},"agent_actions":{"view_html":"https://pith.science/pith/NTVJ7MBGJPIHMY5TUHSJ22DROG","download_json":"https://pith.science/pith/NTVJ7MBGJPIHMY5TUHSJ22DROG.json","view_paper":"https://pith.science/paper/NTVJ7MBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13580&json=true","fetch_graph":"https://pith.science/api/pith-number/NTVJ7MBGJPIHMY5TUHSJ22DROG/graph.json","fetch_events":"https://pith.science/api/pith-number/NTVJ7MBGJPIHMY5TUHSJ22DROG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTVJ7MBGJPIHMY5TUHSJ22DROG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTVJ7MBGJPIHMY5TUHSJ22DROG/action/storage_attestation","attest_author":"https://pith.science/pith/NTVJ7MBGJPIHMY5TUHSJ22DROG/action/author_attestation","sign_citation":"https://pith.science/pith/NTVJ7MBGJPIHMY5TUHSJ22DROG/action/citation_signature","submit_replication":"https://pith.science/pith/NTVJ7MBGJPIHMY5TUHSJ22DROG/action/replication_record"}},"created_at":"2026-07-05T11:03:59.276798+00:00","updated_at":"2026-07-05T11:03:59.276798+00:00"}