{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TFJV462TKHNXNM5UQATNBKDG3W","short_pith_number":"pith:TFJV462T","schema_version":"1.0","canonical_sha256":"99535e7b5351db76b3b48026d0a866dda7b3dfcc33cbc84f52b6d7b56b5c1aef","source":{"kind":"arxiv","id":"2412.03934","version":2},"attestation_state":"computed","paper":{"title":"InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Jiahui Huang, Jiawei Yang, Jun Gao, Mike Chen, Sanja Fidler, Siheng Chen, Tianchang Shen, Xuanchi Ren, Yifan Lu, Yue Wang, Zhangjie Wu","submitted_at":"2024-12-05T07:32:20Z","abstract_excerpt":"We present InfiniCube, a scalable method for generating unbounded dynamic 3D driving scenes with high fidelity and controllability. Previous methods for scene generation either suffer from limited scales or lack geometric and appearance consistency along generated sequences. In contrast, we leverage the recent advancements in scalable 3D representation and video models to achieve large dynamic scene generation that allows flexible controls through HD maps, vehicle bounding boxes, and text descriptions. First, we construct a map-conditioned sparse-voxel-based 3D generative model to unleash its "},"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":"2412.03934","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T07:32:20Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"9a50e674ad95cce23974d08b38cf4fb1e59387a0bb4775e71dc1dc54504a4e51","abstract_canon_sha256":"dad8d960812f8bf487fb15c162bc537eb0dd6b6c5b178718cf238cf14005b8e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:22.298420Z","signature_b64":"n2Vls7eFJL0cPAdSBMfU+g33sbfqUHjBjqePHaRHC3OaeiQmUSG6C3PoWs6/YGpojDJ22EG+BXJ5qD+YDgJdAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99535e7b5351db76b3b48026d0a866dda7b3dfcc33cbc84f52b6d7b56b5c1aef","last_reissued_at":"2026-07-05T11:27:22.297918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:22.297918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Jiahui Huang, Jiawei Yang, Jun Gao, Mike Chen, Sanja Fidler, Siheng Chen, Tianchang Shen, Xuanchi Ren, Yifan Lu, Yue Wang, Zhangjie Wu","submitted_at":"2024-12-05T07:32:20Z","abstract_excerpt":"We present InfiniCube, a scalable method for generating unbounded dynamic 3D driving scenes with high fidelity and controllability. Previous methods for scene generation either suffer from limited scales or lack geometric and appearance consistency along generated sequences. In contrast, we leverage the recent advancements in scalable 3D representation and video models to achieve large dynamic scene generation that allows flexible controls through HD maps, vehicle bounding boxes, and text descriptions. First, we construct a map-conditioned sparse-voxel-based 3D generative model to unleash its "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03934","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/2412.03934/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":"2412.03934","created_at":"2026-07-05T11:27:22.297977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03934v2","created_at":"2026-07-05T11:27:22.297977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03934","created_at":"2026-07-05T11:27:22.297977+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFJV462TKHNX","created_at":"2026-07-05T11:27:22.297977+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFJV462TKHNXNM5U","created_at":"2026-07-05T11:27:22.297977+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFJV462T","created_at":"2026-07-05T11:27:22.297977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24138","citing_title":"Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31109","citing_title":"InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16395","citing_title":"OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22039","citing_title":"SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00781","citing_title":"Map2World: Segment Map Conditioned Text to 3D World Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13036","citing_title":"Lyra 2.0: Explorable Generative 3D Worlds","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04887","citing_title":"HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14025","citing_title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","ref_index":250,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TFJV462TKHNXNM5UQATNBKDG3W","json":"https://pith.science/pith/TFJV462TKHNXNM5UQATNBKDG3W.json","graph_json":"https://pith.science/api/pith-number/TFJV462TKHNXNM5UQATNBKDG3W/graph.json","events_json":"https://pith.science/api/pith-number/TFJV462TKHNXNM5UQATNBKDG3W/events.json","paper":"https://pith.science/paper/TFJV462T"},"agent_actions":{"view_html":"https://pith.science/pith/TFJV462TKHNXNM5UQATNBKDG3W","download_json":"https://pith.science/pith/TFJV462TKHNXNM5UQATNBKDG3W.json","view_paper":"https://pith.science/paper/TFJV462T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03934&json=true","fetch_graph":"https://pith.science/api/pith-number/TFJV462TKHNXNM5UQATNBKDG3W/graph.json","fetch_events":"https://pith.science/api/pith-number/TFJV462TKHNXNM5UQATNBKDG3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFJV462TKHNXNM5UQATNBKDG3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFJV462TKHNXNM5UQATNBKDG3W/action/storage_attestation","attest_author":"https://pith.science/pith/TFJV462TKHNXNM5UQATNBKDG3W/action/author_attestation","sign_citation":"https://pith.science/pith/TFJV462TKHNXNM5UQATNBKDG3W/action/citation_signature","submit_replication":"https://pith.science/pith/TFJV462TKHNXNM5UQATNBKDG3W/action/replication_record"}},"created_at":"2026-07-05T11:27:22.297977+00:00","updated_at":"2026-07-05T11:27:22.297977+00:00"}