{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UTWLRBQPVMEAZTW53BVSRD5JOA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"99c7f59f9a2b0286ca5bf29614bbe60b0df176d585038803895fe1e9e73acdf9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-15T15:04:27Z","title_canon_sha256":"820bbc84f440e1a4e83bb6c72e2ff5b79b3032f7e51a1dc3f07ebfdbe51eb550"},"schema_version":"1.0","source":{"id":"2412.11210","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11210","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11210v2","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11210","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"pith_short_12","alias_value":"UTWLRBQPVMEA","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"pith_short_16","alias_value":"UTWLRBQPVMEAZTW5","created_at":"2026-07-05T09:59:21Z"},{"alias_kind":"pith_short_8","alias_value":"UTWLRBQP","created_at":"2026-07-05T09:59:21Z"}],"graph_snapshots":[{"event_id":"sha256:b4642913e40520f1393fbf4da2c8214e1afe2e2ca249bfbd80e2abe805b50575","target":"graph","created_at":"2026-07-05T09:59:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.11210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inferring the 3D structure of a scene from a single image is an ill-posed and challenging problem in the field of vision-centric autonomous driving. Existing methods usually employ neural radiance fields to produce voxelized 3D occupancy, lacking instance-level semantic reasoning and temporal photometric consistency. In this paper, we propose ViPOcc, which leverages the visual priors from vision foundation models (VFMs) for fine-grained 3D occupancy prediction. Unlike previous works that solely employ volume rendering for RGB and depth image reconstruction, we introduce a metric depth estimati","authors_text":"Rui Fan, Tanghui Li, Xijing Zhang, Yanting Zhang, Yi Feng, Yu Han","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-15T15:04:27Z","title":"ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11210","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bf5ec85eec022c32b0363a0433a7ace5ada398ac8d41d374eaec77e9a523d1d0","target":"record","created_at":"2026-07-05T09:59:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"99c7f59f9a2b0286ca5bf29614bbe60b0df176d585038803895fe1e9e73acdf9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-15T15:04:27Z","title_canon_sha256":"820bbc84f440e1a4e83bb6c72e2ff5b79b3032f7e51a1dc3f07ebfdbe51eb550"},"schema_version":"1.0","source":{"id":"2412.11210","kind":"arxiv","version":2}},"canonical_sha256":"a4ecb8860fab080cceddd86b288fa970338fd6e1dfa1f0032363a785d5a6c428","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4ecb8860fab080cceddd86b288fa970338fd6e1dfa1f0032363a785d5a6c428","first_computed_at":"2026-07-05T09:59:21.391841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:21.391841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+lDFLi45+0KHWohI8hw0m3vha8DNuQuTADtQHuUHEv8vjnyaYiuK/lLIlF9mwk5F87HFn8oIvjfiiO4829BtAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:21.392359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11210","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf5ec85eec022c32b0363a0433a7ace5ada398ac8d41d374eaec77e9a523d1d0","sha256:b4642913e40520f1393fbf4da2c8214e1afe2e2ca249bfbd80e2abe805b50575"],"state_sha256":"bf58cbaaab471efabed16216595f5fd268ce34e48bb3064654b5f06f924ecf30"}