{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:65FNWAVOVERPR6FSONGVYCHJ7O","short_pith_number":"pith:65FNWAVO","schema_version":"1.0","canonical_sha256":"f74adb02aea922f8f8b2734d5c08e9fba99a76a3d864f6ae0cc1921556331811","source":{"kind":"arxiv","id":"2307.01492","version":1},"attestation_state":"computed","paper":{"title":"FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"David Austin, Jan Kautz, Jose M. Alvarez, Mingsheng Fang, Shiyi Lan, Zhiding Yu, Zhiqi Li","submitted_at":"2023-07-04T05:55:54Z","abstract_excerpt":"This technical report summarizes the winning solution for the 3D Occupancy Prediction Challenge, which is held in conjunction with the CVPR 2023 Workshop on End-to-End Autonomous Driving and CVPR 23 Workshop on Vision-Centric Autonomous Driving Workshop. Our proposed solution FB-OCC builds upon FB-BEV, a cutting-edge camera-based bird's-eye view perception design using forward-backward projection. On top of FB-BEV, we further study novel designs and optimization tailored to the 3D occupancy prediction task, including joint depth-semantic pre-training, joint voxel-BEV representation, model scal"},"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":"2307.01492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-04T05:55:54Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"2bab99bab34677df93cfcb129b4c8234cd42e3c7cc2458734a25e2bbba21298c","abstract_canon_sha256":"470857b1d36469aff884ee9d66a951388c5085d4986ec27fe4375dd8066e4e9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:57.239696Z","signature_b64":"1bTQa48T5oKyO0oD74gIy/OwmPbvDjCZOoUXGVmPW2+uujSiqjjk3FI425oXs5l/Zjtxx5XxyiCX0urC/X+UDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f74adb02aea922f8f8b2734d5c08e9fba99a76a3d864f6ae0cc1921556331811","last_reissued_at":"2026-07-05T06:27:57.239294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:57.239294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"David Austin, Jan Kautz, Jose M. Alvarez, Mingsheng Fang, Shiyi Lan, Zhiding Yu, Zhiqi Li","submitted_at":"2023-07-04T05:55:54Z","abstract_excerpt":"This technical report summarizes the winning solution for the 3D Occupancy Prediction Challenge, which is held in conjunction with the CVPR 2023 Workshop on End-to-End Autonomous Driving and CVPR 23 Workshop on Vision-Centric Autonomous Driving Workshop. Our proposed solution FB-OCC builds upon FB-BEV, a cutting-edge camera-based bird's-eye view perception design using forward-backward projection. On top of FB-BEV, we further study novel designs and optimization tailored to the 3D occupancy prediction task, including joint depth-semantic pre-training, joint voxel-BEV representation, model scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01492","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/2307.01492/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":"2307.01492","created_at":"2026-07-05T06:27:57.239360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01492v1","created_at":"2026-07-05T06:27:57.239360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01492","created_at":"2026-07-05T06:27:57.239360+00:00"},{"alias_kind":"pith_short_12","alias_value":"65FNWAVOVERP","created_at":"2026-07-05T06:27:57.239360+00:00"},{"alias_kind":"pith_short_16","alias_value":"65FNWAVOVERPR6FS","created_at":"2026-07-05T06:27:57.239360+00:00"},{"alias_kind":"pith_short_8","alias_value":"65FNWAVO","created_at":"2026-07-05T06:27:57.239360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22971","citing_title":"Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI","ref_index":221,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13460","citing_title":"VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03581","citing_title":"UnsOcc: 3D Semantic Occupancy Prediction in Unstructured Scene via Rendering Fusion","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01030","citing_title":"Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22667","citing_title":"Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22039","citing_title":"SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06400","citing_title":"TFusionOcc: T-Primitive Based Object-Centric Multi-Sensor Fusion Framework for 3D Occupancy Prediction","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02930","citing_title":"BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28115","citing_title":"FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05072","citing_title":"Height-Guided Projection Reparameterization for Camera-LiDAR Occupancy","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05072","citing_title":"Height-Guided Projection Reparameterization for Camera-LiDAR Occupancy","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05780","citing_title":"Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65FNWAVOVERPR6FSONGVYCHJ7O","json":"https://pith.science/pith/65FNWAVOVERPR6FSONGVYCHJ7O.json","graph_json":"https://pith.science/api/pith-number/65FNWAVOVERPR6FSONGVYCHJ7O/graph.json","events_json":"https://pith.science/api/pith-number/65FNWAVOVERPR6FSONGVYCHJ7O/events.json","paper":"https://pith.science/paper/65FNWAVO"},"agent_actions":{"view_html":"https://pith.science/pith/65FNWAVOVERPR6FSONGVYCHJ7O","download_json":"https://pith.science/pith/65FNWAVOVERPR6FSONGVYCHJ7O.json","view_paper":"https://pith.science/paper/65FNWAVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01492&json=true","fetch_graph":"https://pith.science/api/pith-number/65FNWAVOVERPR6FSONGVYCHJ7O/graph.json","fetch_events":"https://pith.science/api/pith-number/65FNWAVOVERPR6FSONGVYCHJ7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65FNWAVOVERPR6FSONGVYCHJ7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65FNWAVOVERPR6FSONGVYCHJ7O/action/storage_attestation","attest_author":"https://pith.science/pith/65FNWAVOVERPR6FSONGVYCHJ7O/action/author_attestation","sign_citation":"https://pith.science/pith/65FNWAVOVERPR6FSONGVYCHJ7O/action/citation_signature","submit_replication":"https://pith.science/pith/65FNWAVOVERPR6FSONGVYCHJ7O/action/replication_record"}},"created_at":"2026-07-05T06:27:57.239360+00:00","updated_at":"2026-07-05T06:27:57.239360+00:00"}