{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VOHQRM473HC76DU7HUBPCDNBI2","short_pith_number":"pith:VOHQRM47","schema_version":"1.0","canonical_sha256":"ab8f08b39fd9c5ff0e9f3d02f10da1469a4b8d745d6f3a75b1e0d30a8cf0c778","source":{"kind":"arxiv","id":"2407.06516","version":2},"attestation_state":"computed","paper":{"title":"VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Liu, Guile Wu, Jinjun Shan, Kejian Lin, Yang Liu, Yibo Liu, Yuan Ren, Zheyuan Yang","submitted_at":"2024-07-09T03:09:55Z","abstract_excerpt":"Generating 3D vehicle assets from in-the-wild observations is crucial to autonomous driving. Existing image-to-3D methods cannot well address this problem because they learn generation merely from image RGB information without a deeper understanding of in-the-wild vehicles (such as car models, manufacturers, etc.). This leads to their poor zero-shot prediction capability to handle real-world observations with occlusion or tricky viewing angles. To solve this problem, in this work, we propose VQA-Diff, a novel framework that leverages in-the-wild vehicle images to create photorealistic 3D vehic"},"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":"2407.06516","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T03:09:55Z","cross_cats_sorted":[],"title_canon_sha256":"b6813e8e4db9bd1940346332e1bf1c75f3fd8554e481ce368b85be60002fbebb","abstract_canon_sha256":"9fc8cb2fccfc718514931a6074254981447adc4ff82b7932d0d8943cb4deaac7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:38.707538Z","signature_b64":"R8iacJt0Lkv08eerrgIsnfIy6MT+ImcmGjRCHdtP+Kc5QRFtzZWVXNDGGeVe/XzdYqaFI2Ue3Zdwafqvl/aeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab8f08b39fd9c5ff0e9f3d02f10da1469a4b8d745d6f3a75b1e0d30a8cf0c778","last_reissued_at":"2026-07-05T08:42:38.707045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:38.707045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Liu, Guile Wu, Jinjun Shan, Kejian Lin, Yang Liu, Yibo Liu, Yuan Ren, Zheyuan Yang","submitted_at":"2024-07-09T03:09:55Z","abstract_excerpt":"Generating 3D vehicle assets from in-the-wild observations is crucial to autonomous driving. Existing image-to-3D methods cannot well address this problem because they learn generation merely from image RGB information without a deeper understanding of in-the-wild vehicles (such as car models, manufacturers, etc.). This leads to their poor zero-shot prediction capability to handle real-world observations with occlusion or tricky viewing angles. To solve this problem, in this work, we propose VQA-Diff, a novel framework that leverages in-the-wild vehicle images to create photorealistic 3D vehic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06516","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/2407.06516/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":"2407.06516","created_at":"2026-07-05T08:42:38.707104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06516v2","created_at":"2026-07-05T08:42:38.707104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06516","created_at":"2026-07-05T08:42:38.707104+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOHQRM473HC7","created_at":"2026-07-05T08:42:38.707104+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOHQRM473HC76DU7","created_at":"2026-07-05T08:42:38.707104+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOHQRM47","created_at":"2026-07-05T08:42:38.707104+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/VOHQRM473HC76DU7HUBPCDNBI2","json":"https://pith.science/pith/VOHQRM473HC76DU7HUBPCDNBI2.json","graph_json":"https://pith.science/api/pith-number/VOHQRM473HC76DU7HUBPCDNBI2/graph.json","events_json":"https://pith.science/api/pith-number/VOHQRM473HC76DU7HUBPCDNBI2/events.json","paper":"https://pith.science/paper/VOHQRM47"},"agent_actions":{"view_html":"https://pith.science/pith/VOHQRM473HC76DU7HUBPCDNBI2","download_json":"https://pith.science/pith/VOHQRM473HC76DU7HUBPCDNBI2.json","view_paper":"https://pith.science/paper/VOHQRM47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06516&json=true","fetch_graph":"https://pith.science/api/pith-number/VOHQRM473HC76DU7HUBPCDNBI2/graph.json","fetch_events":"https://pith.science/api/pith-number/VOHQRM473HC76DU7HUBPCDNBI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOHQRM473HC76DU7HUBPCDNBI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOHQRM473HC76DU7HUBPCDNBI2/action/storage_attestation","attest_author":"https://pith.science/pith/VOHQRM473HC76DU7HUBPCDNBI2/action/author_attestation","sign_citation":"https://pith.science/pith/VOHQRM473HC76DU7HUBPCDNBI2/action/citation_signature","submit_replication":"https://pith.science/pith/VOHQRM473HC76DU7HUBPCDNBI2/action/replication_record"}},"created_at":"2026-07-05T08:42:38.707104+00:00","updated_at":"2026-07-05T08:42:38.707104+00:00"}