{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZU4EDCKYZT63ARFBUPSY67SQZT","short_pith_number":"pith:ZU4EDCKY","schema_version":"1.0","canonical_sha256":"cd38418958ccfdb044a1a3e58f7e50cccfff950b0d39078f9e8fc13993399476","source":{"kind":"arxiv","id":"2409.11356","version":2},"attestation_state":"computed","paper":{"title":"RenderWorld: World Model with Self-Supervised 3D Label","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fabio Remondino, Haozhe Wang, Jingwen Liu, Liu Haiyang, Wenzhen Dong, Yan Wang, Yihua Shao, Yuexin Ma, Yuhang Lu, Zhe Wang, Ziyang Yan","submitted_at":"2024-09-17T17:00:52Z","abstract_excerpt":"End-to-end autonomous driving with vision-only is not only more cost-effective compared to LiDAR-vision fusion but also more reliable than traditional methods. To achieve a economical and robust purely visual autonomous driving system, we propose RenderWorld, a vision-only end-to-end autonomous driving framework, which generates 3D occupancy labels using a self-supervised gaussian-based Img2Occ Module, then encodes the labels by AM-VAE, and uses world model for forecasting and planning. RenderWorld employs Gaussian Splatting to represent 3D scenes and render 2D images greatly improves segmenta"},"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":"2409.11356","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-17T17:00:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eca3a1001b381ad44927887aaf5755ddd0160c2c104a24a40b12ff0b8a993159","abstract_canon_sha256":"a1ff06f0046dfb72c6e863d463ffe9e2cb4e2d20dd60bf0781b0671796607521"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:43.026632Z","signature_b64":"GsBCTlX+H+G5b+PyrMeVqJHX2x4G26W9r9gCC3H8j836aba3EVLywcsbuESDm6VHmKXKScZZTMH8dQ6YGfFLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd38418958ccfdb044a1a3e58f7e50cccfff950b0d39078f9e8fc13993399476","last_reissued_at":"2026-07-05T10:13:43.026140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:43.026140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RenderWorld: World Model with Self-Supervised 3D Label","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fabio Remondino, Haozhe Wang, Jingwen Liu, Liu Haiyang, Wenzhen Dong, Yan Wang, Yihua Shao, Yuexin Ma, Yuhang Lu, Zhe Wang, Ziyang Yan","submitted_at":"2024-09-17T17:00:52Z","abstract_excerpt":"End-to-end autonomous driving with vision-only is not only more cost-effective compared to LiDAR-vision fusion but also more reliable than traditional methods. To achieve a economical and robust purely visual autonomous driving system, we propose RenderWorld, a vision-only end-to-end autonomous driving framework, which generates 3D occupancy labels using a self-supervised gaussian-based Img2Occ Module, then encodes the labels by AM-VAE, and uses world model for forecasting and planning. RenderWorld employs Gaussian Splatting to represent 3D scenes and render 2D images greatly improves segmenta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11356","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/2409.11356/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":"2409.11356","created_at":"2026-07-05T10:13:43.026199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11356v2","created_at":"2026-07-05T10:13:43.026199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11356","created_at":"2026-07-05T10:13:43.026199+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZU4EDCKYZT63","created_at":"2026-07-05T10:13:43.026199+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZU4EDCKYZT63ARFB","created_at":"2026-07-05T10:13:43.026199+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZU4EDCKY","created_at":"2026-07-05T10:13:43.026199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06401","citing_title":"A Definition and Roadmap for World Models","ref_index":201,"is_internal_anchor":true},{"citing_arxiv_id":"2606.04945","citing_title":"STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27644","citing_title":"CascadeOcc: Rethinking 3D Occupancy World Models with Cascaded VQ Representations","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2412.12870","citing_title":"Physically Interpretable World Models via Weakly Supervised Representation Learning","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22039","citing_title":"SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZU4EDCKYZT63ARFBUPSY67SQZT","json":"https://pith.science/pith/ZU4EDCKYZT63ARFBUPSY67SQZT.json","graph_json":"https://pith.science/api/pith-number/ZU4EDCKYZT63ARFBUPSY67SQZT/graph.json","events_json":"https://pith.science/api/pith-number/ZU4EDCKYZT63ARFBUPSY67SQZT/events.json","paper":"https://pith.science/paper/ZU4EDCKY"},"agent_actions":{"view_html":"https://pith.science/pith/ZU4EDCKYZT63ARFBUPSY67SQZT","download_json":"https://pith.science/pith/ZU4EDCKYZT63ARFBUPSY67SQZT.json","view_paper":"https://pith.science/paper/ZU4EDCKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11356&json=true","fetch_graph":"https://pith.science/api/pith-number/ZU4EDCKYZT63ARFBUPSY67SQZT/graph.json","fetch_events":"https://pith.science/api/pith-number/ZU4EDCKYZT63ARFBUPSY67SQZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZU4EDCKYZT63ARFBUPSY67SQZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZU4EDCKYZT63ARFBUPSY67SQZT/action/storage_attestation","attest_author":"https://pith.science/pith/ZU4EDCKYZT63ARFBUPSY67SQZT/action/author_attestation","sign_citation":"https://pith.science/pith/ZU4EDCKYZT63ARFBUPSY67SQZT/action/citation_signature","submit_replication":"https://pith.science/pith/ZU4EDCKYZT63ARFBUPSY67SQZT/action/replication_record"}},"created_at":"2026-07-05T10:13:43.026199+00:00","updated_at":"2026-07-05T10:13:43.026199+00:00"}