{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZUIVIIFGHRGFTYT23CJGVU3YTE","short_pith_number":"pith:ZUIVIIFG","schema_version":"1.0","canonical_sha256":"cd115420a63c4c59e27ad8926ad3789903210171777b9af90f8a9ef94820945e","source":{"kind":"arxiv","id":"2412.14494","version":1},"attestation_state":"computed","paper":{"title":"Drive-1-to-3: Enriching Diffusion Priors for Novel View Synthesis of Real Vehicles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Zhuang, Chuang Lin, Jianfei Cai, Manmohan Chandraker, Shanlin Sun, Ziyu Jiang","submitted_at":"2024-12-19T03:39:13Z","abstract_excerpt":"The recent advent of large-scale 3D data, e.g. Objaverse, has led to impressive progress in training pose-conditioned diffusion models for novel view synthesis. However, due to the synthetic nature of such 3D data, their performance drops significantly when applied to real-world images. This paper consolidates a set of good practices to finetune large pretrained models for a real-world task -- harvesting vehicle assets for autonomous driving applications. To this end, we delve into the discrepancies between the synthetic data and real driving data, then develop several strategies to account fo"},"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":"2412.14494","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T03:39:13Z","cross_cats_sorted":[],"title_canon_sha256":"57f1c8b7217ecd90e40d1f0032d02a7af133a794ac2a7ee257f7e981d9b449a6","abstract_canon_sha256":"728019308b389489b752d9c150d6695db5a0b7f8dadb463124a1e263ea807395"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:48.207200Z","signature_b64":"mTDaIP2Yw2b1z9lQOjQ1/Yt/CBlXIvnxEaVOVHnqcCJ6Ffmr5YIsVsEqFiwZn555bBnaD0tuKtQwowHb9YuRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd115420a63c4c59e27ad8926ad3789903210171777b9af90f8a9ef94820945e","last_reissued_at":"2026-07-05T09:51:48.206698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:48.206698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Drive-1-to-3: Enriching Diffusion Priors for Novel View Synthesis of Real Vehicles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Zhuang, Chuang Lin, Jianfei Cai, Manmohan Chandraker, Shanlin Sun, Ziyu Jiang","submitted_at":"2024-12-19T03:39:13Z","abstract_excerpt":"The recent advent of large-scale 3D data, e.g. Objaverse, has led to impressive progress in training pose-conditioned diffusion models for novel view synthesis. However, due to the synthetic nature of such 3D data, their performance drops significantly when applied to real-world images. This paper consolidates a set of good practices to finetune large pretrained models for a real-world task -- harvesting vehicle assets for autonomous driving applications. To this end, we delve into the discrepancies between the synthetic data and real driving data, then develop several strategies to account fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14494","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/2412.14494/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":"2412.14494","created_at":"2026-07-05T09:51:48.206753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14494v1","created_at":"2026-07-05T09:51:48.206753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14494","created_at":"2026-07-05T09:51:48.206753+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUIVIIFGHRGF","created_at":"2026-07-05T09:51:48.206753+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUIVIIFGHRGFTYT2","created_at":"2026-07-05T09:51:48.206753+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUIVIIFG","created_at":"2026-07-05T09:51:48.206753+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25300","citing_title":"HiFiVe: High-Fidelity Vehicle Generation Leveraging Auto-Regressive 2D Generative Priors","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24257","citing_title":"3DCarGen: Scalable 3D Car Generation via 3D-consistent Multi-view Synthesis","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24301","citing_title":"MM-TRELLIS: Point-Cloud Guided Multi-Modal 3D Vehicle Generation in Autonomous Driving","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24257","citing_title":"3DCarGen: Scalable 3D Car Generation via 3D-consistent Multi-view Synthesis","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25300","citing_title":"HiFiVe: High-Fidelity Vehicle Generation Leveraging Auto-Regressive 2D Generative Priors","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZUIVIIFGHRGFTYT23CJGVU3YTE","json":"https://pith.science/pith/ZUIVIIFGHRGFTYT23CJGVU3YTE.json","graph_json":"https://pith.science/api/pith-number/ZUIVIIFGHRGFTYT23CJGVU3YTE/graph.json","events_json":"https://pith.science/api/pith-number/ZUIVIIFGHRGFTYT23CJGVU3YTE/events.json","paper":"https://pith.science/paper/ZUIVIIFG"},"agent_actions":{"view_html":"https://pith.science/pith/ZUIVIIFGHRGFTYT23CJGVU3YTE","download_json":"https://pith.science/pith/ZUIVIIFGHRGFTYT23CJGVU3YTE.json","view_paper":"https://pith.science/paper/ZUIVIIFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14494&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUIVIIFGHRGFTYT23CJGVU3YTE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUIVIIFGHRGFTYT23CJGVU3YTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUIVIIFGHRGFTYT23CJGVU3YTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUIVIIFGHRGFTYT23CJGVU3YTE/action/storage_attestation","attest_author":"https://pith.science/pith/ZUIVIIFGHRGFTYT23CJGVU3YTE/action/author_attestation","sign_citation":"https://pith.science/pith/ZUIVIIFGHRGFTYT23CJGVU3YTE/action/citation_signature","submit_replication":"https://pith.science/pith/ZUIVIIFGHRGFTYT23CJGVU3YTE/action/replication_record"}},"created_at":"2026-07-05T09:51:48.206753+00:00","updated_at":"2026-07-05T09:51:48.206753+00:00"}