{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QUBSNOKGSMTFAYIOXYJ4THIRQ4","short_pith_number":"pith:QUBSNOKG","schema_version":"1.0","canonical_sha256":"850326b946932650610ebe13c99d11873d6fb97932b392300a7f722b7db882ba","source":{"kind":"arxiv","id":"2407.17310","version":2},"attestation_state":"computed","paper":{"title":"LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjamin Risse, Fabian Gigengack, Simon Boeder","submitted_at":"2024-07-24T14:22:55Z","abstract_excerpt":"The 3D occupancy estimation task has become an important challenge in the area of vision-based autonomous driving recently. However, most existing camera-based methods rely on costly 3D voxel labels or LiDAR scans for training, limiting their practicality and scalability. Moreover, most methods are tied to a predefined set of classes which they can detect. In this work we present a novel approach for open vocabulary occupancy estimation called LangOcc, that is trained only via camera images, and can detect arbitrary semantics via vision-language alignment. In particular, we distill the knowled"},"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":"2407.17310","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-24T14:22:55Z","cross_cats_sorted":[],"title_canon_sha256":"4e8b81c282e78a7234d13e86105d1d43ef0fac7b5a35624c550b879924809929","abstract_canon_sha256":"395bac6303e7b21df52aaddeba01e8ecee7cb33b8dfd5d6c9253cbc466a047e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:16.259793Z","signature_b64":"kllsACLG4hfmvlre7CF39b9rbIQojdpssXH0d4xbM4yDYw4BJOD4Ti6IWQ4uz8wzc27mN5EdtnG9qu60Bm23BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"850326b946932650610ebe13c99d11873d6fb97932b392300a7f722b7db882ba","last_reissued_at":"2026-07-05T08:48:16.259409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:16.259409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjamin Risse, Fabian Gigengack, Simon Boeder","submitted_at":"2024-07-24T14:22:55Z","abstract_excerpt":"The 3D occupancy estimation task has become an important challenge in the area of vision-based autonomous driving recently. However, most existing camera-based methods rely on costly 3D voxel labels or LiDAR scans for training, limiting their practicality and scalability. Moreover, most methods are tied to a predefined set of classes which they can detect. In this work we present a novel approach for open vocabulary occupancy estimation called LangOcc, that is trained only via camera images, and can detect arbitrary semantics via vision-language alignment. In particular, we distill the knowled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17310","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/2407.17310/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":"2407.17310","created_at":"2026-07-05T08:48:16.259465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17310v2","created_at":"2026-07-05T08:48:16.259465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17310","created_at":"2026-07-05T08:48:16.259465+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUBSNOKGSMTF","created_at":"2026-07-05T08:48:16.259465+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUBSNOKGSMTFAYIO","created_at":"2026-07-05T08:48:16.259465+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUBSNOKG","created_at":"2026-07-05T08:48:16.259465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13460","citing_title":"VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28587","citing_title":"Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22667","citing_title":"Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QUBSNOKGSMTFAYIOXYJ4THIRQ4","json":"https://pith.science/pith/QUBSNOKGSMTFAYIOXYJ4THIRQ4.json","graph_json":"https://pith.science/api/pith-number/QUBSNOKGSMTFAYIOXYJ4THIRQ4/graph.json","events_json":"https://pith.science/api/pith-number/QUBSNOKGSMTFAYIOXYJ4THIRQ4/events.json","paper":"https://pith.science/paper/QUBSNOKG"},"agent_actions":{"view_html":"https://pith.science/pith/QUBSNOKGSMTFAYIOXYJ4THIRQ4","download_json":"https://pith.science/pith/QUBSNOKGSMTFAYIOXYJ4THIRQ4.json","view_paper":"https://pith.science/paper/QUBSNOKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17310&json=true","fetch_graph":"https://pith.science/api/pith-number/QUBSNOKGSMTFAYIOXYJ4THIRQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/QUBSNOKGSMTFAYIOXYJ4THIRQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUBSNOKGSMTFAYIOXYJ4THIRQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUBSNOKGSMTFAYIOXYJ4THIRQ4/action/storage_attestation","attest_author":"https://pith.science/pith/QUBSNOKGSMTFAYIOXYJ4THIRQ4/action/author_attestation","sign_citation":"https://pith.science/pith/QUBSNOKGSMTFAYIOXYJ4THIRQ4/action/citation_signature","submit_replication":"https://pith.science/pith/QUBSNOKGSMTFAYIOXYJ4THIRQ4/action/replication_record"}},"created_at":"2026-07-05T08:48:16.259465+00:00","updated_at":"2026-07-05T08:48:16.259465+00:00"}