{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VOHQRM473HC76DU7HUBPCDNBI2","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":"9fc8cb2fccfc718514931a6074254981447adc4ff82b7932d0d8943cb4deaac7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T03:09:55Z","title_canon_sha256":"b6813e8e4db9bd1940346332e1bf1c75f3fd8554e481ce368b85be60002fbebb"},"schema_version":"1.0","source":{"id":"2407.06516","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.06516","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.06516v2","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06516","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"pith_short_12","alias_value":"VOHQRM473HC7","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"pith_short_16","alias_value":"VOHQRM473HC76DU7","created_at":"2026-07-05T08:42:38Z"},{"alias_kind":"pith_short_8","alias_value":"VOHQRM47","created_at":"2026-07-05T08:42:38Z"}],"graph_snapshots":[{"event_id":"sha256:44d9db170bdff3b55b415a09387362e51627d26c8aa58056b1963cf92cceee6c","target":"graph","created_at":"2026-07-05T08:42:38Z","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/2407.06516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bingbing Liu, Guile Wu, Jinjun Shan, Kejian Lin, Yang Liu, Yibo Liu, Yuan Ren, Zheyuan Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T03:09:55Z","title":"VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06516","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:d12c66d2d04124902a2e66da1a9ce4bcc033956e2c40fbc3daee939453186862","target":"record","created_at":"2026-07-05T08:42:38Z","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":"9fc8cb2fccfc718514931a6074254981447adc4ff82b7932d0d8943cb4deaac7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T03:09:55Z","title_canon_sha256":"b6813e8e4db9bd1940346332e1bf1c75f3fd8554e481ce368b85be60002fbebb"},"schema_version":"1.0","source":{"id":"2407.06516","kind":"arxiv","version":2}},"canonical_sha256":"ab8f08b39fd9c5ff0e9f3d02f10da1469a4b8d745d6f3a75b1e0d30a8cf0c778","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab8f08b39fd9c5ff0e9f3d02f10da1469a4b8d745d6f3a75b1e0d30a8cf0c778","first_computed_at":"2026-07-05T08:42:38.707045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:38.707045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R8iacJt0Lkv08eerrgIsnfIy6MT+ImcmGjRCHdtP+Kc5QRFtzZWVXNDGGeVe/XzdYqaFI2Ue3Zdwafqvl/aeBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:38.707538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.06516","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d12c66d2d04124902a2e66da1a9ce4bcc033956e2c40fbc3daee939453186862","sha256:44d9db170bdff3b55b415a09387362e51627d26c8aa58056b1963cf92cceee6c"],"state_sha256":"2a4cc2c648d122a5469043d8b0e0085ab9ea612c40e262b0a7e92c8acf337bb9"}