{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IL223ASJVWEBNPG2N5UKC4DPS6","short_pith_number":"pith:IL223ASJ","schema_version":"1.0","canonical_sha256":"42f5ad8249ad8816bcda6f68a1706f97a852e9f75629c7be91e0aaad3e070b60","source":{"kind":"arxiv","id":"2409.12753","version":2},"attestation_state":"computed","paper":{"title":"DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lizhuang Ma, Qijian Tian, Xin Tan, Yuan Xie","submitted_at":"2024-09-19T13:16:04Z","abstract_excerpt":"We propose DrivingForward, a feed-forward Gaussian Splatting model that reconstructs driving scenes from flexible surround-view input. Driving scene images from vehicle-mounted cameras are typically sparse, with limited overlap, and the movement of the vehicle further complicates the acquisition of camera extrinsics. To tackle these challenges and achieve real-time reconstruction, we jointly train a pose network, a depth network, and a Gaussian network to predict the Gaussian primitives that represent the driving scenes. The pose network and depth network determine the position of the Gaussian"},"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":"2409.12753","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-19T13:16:04Z","cross_cats_sorted":[],"title_canon_sha256":"1a60993e8be31cce94d161c26e2fa473f8ac39cd3dfaeb127345212e63cf8272","abstract_canon_sha256":"31d4babf9fd82ecb85f691780fbfbd397393fb8a21812686f807dcfb7fc72dfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:39.819221Z","signature_b64":"k2IGMtlo678xiuL4g04LHboqrz+k3Nvrm5Sa48rcWeBukER61A67GQ18FW1Je1TYTqfB2ceFV6yUBjVcu1aIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42f5ad8249ad8816bcda6f68a1706f97a852e9f75629c7be91e0aaad3e070b60","last_reissued_at":"2026-07-05T09:52:39.818817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:39.818817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lizhuang Ma, Qijian Tian, Xin Tan, Yuan Xie","submitted_at":"2024-09-19T13:16:04Z","abstract_excerpt":"We propose DrivingForward, a feed-forward Gaussian Splatting model that reconstructs driving scenes from flexible surround-view input. Driving scene images from vehicle-mounted cameras are typically sparse, with limited overlap, and the movement of the vehicle further complicates the acquisition of camera extrinsics. To tackle these challenges and achieve real-time reconstruction, we jointly train a pose network, a depth network, and a Gaussian network to predict the Gaussian primitives that represent the driving scenes. The pose network and depth network determine the position of the Gaussian"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12753","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/2409.12753/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":"2409.12753","created_at":"2026-07-05T09:52:39.818866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12753v2","created_at":"2026-07-05T09:52:39.818866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12753","created_at":"2026-07-05T09:52:39.818866+00:00"},{"alias_kind":"pith_short_12","alias_value":"IL223ASJVWEB","created_at":"2026-07-05T09:52:39.818866+00:00"},{"alias_kind":"pith_short_16","alias_value":"IL223ASJVWEBNPG2","created_at":"2026-07-05T09:52:39.818866+00:00"},{"alias_kind":"pith_short_8","alias_value":"IL223ASJ","created_at":"2026-07-05T09:52:39.818866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04981","citing_title":"AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IL223ASJVWEBNPG2N5UKC4DPS6","json":"https://pith.science/pith/IL223ASJVWEBNPG2N5UKC4DPS6.json","graph_json":"https://pith.science/api/pith-number/IL223ASJVWEBNPG2N5UKC4DPS6/graph.json","events_json":"https://pith.science/api/pith-number/IL223ASJVWEBNPG2N5UKC4DPS6/events.json","paper":"https://pith.science/paper/IL223ASJ"},"agent_actions":{"view_html":"https://pith.science/pith/IL223ASJVWEBNPG2N5UKC4DPS6","download_json":"https://pith.science/pith/IL223ASJVWEBNPG2N5UKC4DPS6.json","view_paper":"https://pith.science/paper/IL223ASJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12753&json=true","fetch_graph":"https://pith.science/api/pith-number/IL223ASJVWEBNPG2N5UKC4DPS6/graph.json","fetch_events":"https://pith.science/api/pith-number/IL223ASJVWEBNPG2N5UKC4DPS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IL223ASJVWEBNPG2N5UKC4DPS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IL223ASJVWEBNPG2N5UKC4DPS6/action/storage_attestation","attest_author":"https://pith.science/pith/IL223ASJVWEBNPG2N5UKC4DPS6/action/author_attestation","sign_citation":"https://pith.science/pith/IL223ASJVWEBNPG2N5UKC4DPS6/action/citation_signature","submit_replication":"https://pith.science/pith/IL223ASJVWEBNPG2N5UKC4DPS6/action/replication_record"}},"created_at":"2026-07-05T09:52:39.818866+00:00","updated_at":"2026-07-05T09:52:39.818866+00:00"}