{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EPT7KWM2EOQEM55HJB3YXHVJJA","short_pith_number":"pith:EPT7KWM2","schema_version":"1.0","canonical_sha256":"23e7f5599a23a04677a748778b9ea94812bcc2ac257d3d30efca8e9d51a48445","source":{"kind":"arxiv","id":"1911.11288","version":2},"attestation_state":"computed","paper":{"title":"Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrien Gaidon, Arjun Bhargava, Sergey Zakharov, Wadim Kehl","submitted_at":"2019-11-26T00:11:49Z","abstract_excerpt":"We present an automatic annotation pipeline to recover 9D cuboids and 3D shapes from pre-trained off-the-shelf 2D detectors and sparse LIDAR data. Our autolabeling method solves an ill-posed inverse problem by considering learned shape priors and optimizing geometric and physical parameters. To address this challenging problem, we apply a novel differentiable shape renderer to signed distance fields (SDF), leveraged together with normalized object coordinate spaces (NOCS). Initially trained on synthetic data to predict shape and coordinates, our method uses these predictions for projective and"},"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":"1911.11288","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-26T00:11:49Z","cross_cats_sorted":[],"title_canon_sha256":"f3ca7a942f31bd1ac43b6cc738e0394818a051e0be2bb2b913dee9496c2e6fb6","abstract_canon_sha256":"533d11989ff5d7ec3bdd2ad2e9b396a413e742991e2faa24cdda4a2a393d5bc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:16.757792Z","signature_b64":"svHorKDuZWFBnKuGFSiz/rxuZpjlHoQYurV/S7m623y02IvW0QM7wziVwqO9j2g6BoaxnBAUTM2EPZhkLCkCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23e7f5599a23a04677a748778b9ea94812bcc2ac257d3d30efca8e9d51a48445","last_reissued_at":"2026-07-05T00:52:16.757428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:16.757428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrien Gaidon, Arjun Bhargava, Sergey Zakharov, Wadim Kehl","submitted_at":"2019-11-26T00:11:49Z","abstract_excerpt":"We present an automatic annotation pipeline to recover 9D cuboids and 3D shapes from pre-trained off-the-shelf 2D detectors and sparse LIDAR data. Our autolabeling method solves an ill-posed inverse problem by considering learned shape priors and optimizing geometric and physical parameters. To address this challenging problem, we apply a novel differentiable shape renderer to signed distance fields (SDF), leveraged together with normalized object coordinate spaces (NOCS). Initially trained on synthetic data to predict shape and coordinates, our method uses these predictions for projective and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.11288","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/1911.11288/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":"1911.11288","created_at":"2026-07-05T00:52:16.757485+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.11288v2","created_at":"2026-07-05T00:52:16.757485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11288","created_at":"2026-07-05T00:52:16.757485+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPT7KWM2EOQE","created_at":"2026-07-05T00:52:16.757485+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPT7KWM2EOQEM55H","created_at":"2026-07-05T00:52:16.757485+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPT7KWM2","created_at":"2026-07-05T00:52:16.757485+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/EPT7KWM2EOQEM55HJB3YXHVJJA","json":"https://pith.science/pith/EPT7KWM2EOQEM55HJB3YXHVJJA.json","graph_json":"https://pith.science/api/pith-number/EPT7KWM2EOQEM55HJB3YXHVJJA/graph.json","events_json":"https://pith.science/api/pith-number/EPT7KWM2EOQEM55HJB3YXHVJJA/events.json","paper":"https://pith.science/paper/EPT7KWM2"},"agent_actions":{"view_html":"https://pith.science/pith/EPT7KWM2EOQEM55HJB3YXHVJJA","download_json":"https://pith.science/pith/EPT7KWM2EOQEM55HJB3YXHVJJA.json","view_paper":"https://pith.science/paper/EPT7KWM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.11288&json=true","fetch_graph":"https://pith.science/api/pith-number/EPT7KWM2EOQEM55HJB3YXHVJJA/graph.json","fetch_events":"https://pith.science/api/pith-number/EPT7KWM2EOQEM55HJB3YXHVJJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPT7KWM2EOQEM55HJB3YXHVJJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPT7KWM2EOQEM55HJB3YXHVJJA/action/storage_attestation","attest_author":"https://pith.science/pith/EPT7KWM2EOQEM55HJB3YXHVJJA/action/author_attestation","sign_citation":"https://pith.science/pith/EPT7KWM2EOQEM55HJB3YXHVJJA/action/citation_signature","submit_replication":"https://pith.science/pith/EPT7KWM2EOQEM55HJB3YXHVJJA/action/replication_record"}},"created_at":"2026-07-05T00:52:16.757485+00:00","updated_at":"2026-07-05T00:52:16.757485+00:00"}