{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DI7RK5SAGPQIJVNIIQRTSU6FCQ","short_pith_number":"pith:DI7RK5SA","schema_version":"1.0","canonical_sha256":"1a3f15764033e084d5a844233953c51424473ae89b65711ac7ddc208a9d01c6b","source":{"kind":"arxiv","id":"2412.13188","version":3},"attestation_state":"computed","paper":{"title":"StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haian Jin, Haotong Lin, Haoyu Guo, Hujun Bao, Kun Zhan, Sida Peng, Xianpeng Lang, Xiaowei Zhou, Yida Wang, Yunzhi Yan, Zhen Xu","submitted_at":"2024-12-17T18:58:55Z","abstract_excerpt":"This paper aims to tackle the problem of photorealistic view synthesis from vehicle sensor data. Recent advancements in neural scene representation have achieved notable success in rendering high-quality autonomous driving scenes, but the performance significantly degrades as the viewpoint deviates from the training trajectory. To mitigate this problem, we introduce StreetCrafter, a novel controllable video diffusion model that utilizes LiDAR point cloud renderings as pixel-level conditions, which fully exploits the generative prior for novel view synthesis, while preserving precise camera con"},"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":"2412.13188","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T18:58:55Z","cross_cats_sorted":[],"title_canon_sha256":"41d0721461621ad9bcafc7793a2672288683d8dedfc27e9fa6b26797a863fda9","abstract_canon_sha256":"e84cb8be3b51c434a1154e48af5e40bb62027d019b246bd36fa51e589c6e6e8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:09.752280Z","signature_b64":"UdEn+bIJH1p0z0CJrr+YQILkZL8yyy+Rc+P8c7KtD2Vn8eQF7Cujd0LKQUGTTGoaJG9N+oHV0k61FVnBuUsWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a3f15764033e084d5a844233953c51424473ae89b65711ac7ddc208a9d01c6b","last_reissued_at":"2026-07-05T11:59:09.751657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:09.751657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haian Jin, Haotong Lin, Haoyu Guo, Hujun Bao, Kun Zhan, Sida Peng, Xianpeng Lang, Xiaowei Zhou, Yida Wang, Yunzhi Yan, Zhen Xu","submitted_at":"2024-12-17T18:58:55Z","abstract_excerpt":"This paper aims to tackle the problem of photorealistic view synthesis from vehicle sensor data. Recent advancements in neural scene representation have achieved notable success in rendering high-quality autonomous driving scenes, but the performance significantly degrades as the viewpoint deviates from the training trajectory. To mitigate this problem, we introduce StreetCrafter, a novel controllable video diffusion model that utilizes LiDAR point cloud renderings as pixel-level conditions, which fully exploits the generative prior for novel view synthesis, while preserving precise camera con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13188","kind":"arxiv","version":3},"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/2412.13188/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":"2412.13188","created_at":"2026-07-05T11:59:09.751734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13188v3","created_at":"2026-07-05T11:59:09.751734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13188","created_at":"2026-07-05T11:59:09.751734+00:00"},{"alias_kind":"pith_short_12","alias_value":"DI7RK5SAGPQI","created_at":"2026-07-05T11:59:09.751734+00:00"},{"alias_kind":"pith_short_16","alias_value":"DI7RK5SAGPQIJVNI","created_at":"2026-07-05T11:59:09.751734+00:00"},{"alias_kind":"pith_short_8","alias_value":"DI7RK5SA","created_at":"2026-07-05T11:59:09.751734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31258","citing_title":"WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DI7RK5SAGPQIJVNIIQRTSU6FCQ","json":"https://pith.science/pith/DI7RK5SAGPQIJVNIIQRTSU6FCQ.json","graph_json":"https://pith.science/api/pith-number/DI7RK5SAGPQIJVNIIQRTSU6FCQ/graph.json","events_json":"https://pith.science/api/pith-number/DI7RK5SAGPQIJVNIIQRTSU6FCQ/events.json","paper":"https://pith.science/paper/DI7RK5SA"},"agent_actions":{"view_html":"https://pith.science/pith/DI7RK5SAGPQIJVNIIQRTSU6FCQ","download_json":"https://pith.science/pith/DI7RK5SAGPQIJVNIIQRTSU6FCQ.json","view_paper":"https://pith.science/paper/DI7RK5SA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13188&json=true","fetch_graph":"https://pith.science/api/pith-number/DI7RK5SAGPQIJVNIIQRTSU6FCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DI7RK5SAGPQIJVNIIQRTSU6FCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DI7RK5SAGPQIJVNIIQRTSU6FCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DI7RK5SAGPQIJVNIIQRTSU6FCQ/action/storage_attestation","attest_author":"https://pith.science/pith/DI7RK5SAGPQIJVNIIQRTSU6FCQ/action/author_attestation","sign_citation":"https://pith.science/pith/DI7RK5SAGPQIJVNIIQRTSU6FCQ/action/citation_signature","submit_replication":"https://pith.science/pith/DI7RK5SAGPQIJVNIIQRTSU6FCQ/action/replication_record"}},"created_at":"2026-07-05T11:59:09.751734+00:00","updated_at":"2026-07-05T11:59:09.751734+00:00"}