{"id":29115368,"url":"https://github.com/worldbench/survey","last_synced_at":"2025-06-29T11:12:55.532Z","repository":{"id":300467247,"uuid":"1005844732","full_name":"worldbench/survey","owner":"worldbench","description":"3D and 4D World Modeling: A Survey","archived":false,"fork":false,"pushed_at":"2025-06-21T21:08:04.000Z","size":5,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-21T21:36:31.432Z","etag":null,"topics":["3d-generation","4d-generation","awesome-list","embodied-ai","lidar-generation","occupancy-generation","spatial-intelligence","video-generation","world-models"],"latest_commit_sha":null,"homepage":"https://worldbench.github.io/survey","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/worldbench.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-06-20T23:42:53.000Z","updated_at":"2025-06-21T21:08:07.000Z","dependencies_parsed_at":"2025-06-21T21:36:34.094Z","dependency_job_id":"9a1f1f57-ad11-42ac-bbcf-5b8910e44bc2","html_url":"https://github.com/worldbench/survey","commit_stats":null,"previous_names":["worldbench/survey"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/worldbench/survey","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/worldbench%2Fsurvey","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/worldbench%2Fsurvey/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/worldbench%2Fsurvey/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/worldbench%2Fsurvey/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/worldbench","download_url":"https://codeload.github.com/worldbench/survey/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/worldbench%2Fsurvey/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262581371,"owners_count":23331913,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["3d-generation","4d-generation","awesome-list","embodied-ai","lidar-generation","occupancy-generation","spatial-intelligence","video-generation","world-models"],"created_at":"2025-06-29T11:07:15.007Z","updated_at":"2025-06-29T11:12:55.520Z","avatar_url":"https://github.com/worldbench.png","language":null,"funding_links":[],"categories":["Other Lists","3D视觉生成重建"],"sub_categories":["TeX Lists","资源传输下载"],"readme":"[![Awesome Logo](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)\n![Visitors](https://komarev.com/ghpvc/?username=worldbench\u0026repo=survey\u0026label=Hello,%20Visitor%20\u0026color=yellow\u0026style=social)\n[![PR's Welcome](https://img.shields.io/badge/PRs-welcome-red.svg?style=flat)](https://github.com/worldbench/survey/pulls)\n\n# :sunglasses: Awesome 3D and 4D World Models\n\n\n\n### Table of Contents\n- [**1. World Modeling from Video Generation**](#1-world-modeling-from-video-generation)\n  - [Data Engine](#one-data-engine)\n  - []()\n  - [Closed-Loop Simulator](#three-closed-loop-simulator)\n  - [Scene Reconstructor](#four-scene-reconstructor)\n- [**2. World Modeling from Occupancy Generation**](#2-world-modeling-from-occupancy-generation)\n  - []()\n  - [Occupancy Forecaster](#two-occupancy-forecaster)\n  - []()\n- [**3. World Modeling from LiDAR Generation**](#3-world-modeling-from-lidar-generation)\n  - []()\n  - []()\n  - []()\n- [**4. Datasets \u0026 Benchmarks**](#4-datasets--benchmarks)\n  - []()\n  - []()\n  - []()\n- [**5. Applications**](#5-applications)\n  - []()\n  - []()\n  - []()\n- [**6. Other Resources**]()\n  - [Workshops]()\n  - [Tutorials]()\n  - [Talks \u0026 Seminars]()\n- [**7. Acknowledgements**]()\n\n\n\n# 1. World Modeling from Video Generation\n\n### :one: Data Engine\n\n\u003e :timer_clock: In chronological order, from the earliest to the latest.\n\n| Model | Paper | Venue | Website | GitHub | \n|:-:|:-|:-:|:-:|:-:|\n||\n| `BEVControl` | [![arXiv](https://img.shields.io/badge/arXiv-2308.01661-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2308.01661)\u003cbr\u003eBEVControl: Accurately Controlling Street-View Elements with Multi-Perspective Consistency via BEV Sketch Layout | arXiv 2023 | - | - |\n| `BEVGen` | [![arXiv](https://img.shields.io/badge/arXiv-2301.04634-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2301.04634)\u003cbr\u003eStreet-View Image Generation from a Bird's-Eye View Layout | RA-L 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://metadriverse.github.io/bevgen/) | [![GitHub](https://img.shields.io/github/stars/alexanderswerdlow/BEVGen)](https://github.com/alexanderswerdlow/BEVGen) |\n| `MagicDrive` | [![arXiv](https://img.shields.io/badge/arXiv-2310.02601-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2310.02601)\u003cbr\u003eMagicDrive: Street View Generation with Diverse 3D Geometry Control | ICLR 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://gaoruiyuan.com/magicdrive/) | [![GitHub](https://img.shields.io/github/stars/cure-lab/MagicDrive)](https://github.com/cure-lab/MagicDrive) |\n| `Panacea` | [![arXiv](https://img.shields.io/badge/arXiv-2311.16813-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2311.16813)\u003cbr\u003ePanacea: Panoramic and Controllable Video Generation for Autonomous Driving | CVPR 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://panacea-ad.github.io/) | [![GitHub](https://img.shields.io/github/stars/wenyuqing/panacea)](https://github.com/wenyuqing/panacea) |\n| `DrivingDiffusion` | [![arXiv](https://img.shields.io/badge/arXiv-2310.07771-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2310.07771)\u003cbr\u003eDrivingDiffusion: Layout-Guided Multi-View Driving Scene Video Generation with Latent Diffusion Model | ECCV 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://drivingdiffusion.github.io/) | [![GitHub](https://img.shields.io/github/stars/shalfun/DrivingDiffusion)](https://github.com/shalfun/DrivingDiffusion) |\n| `WoVoGen` | [![arXiv](https://img.shields.io/badge/arXiv-2312.02934-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2312.02934)\u003cbr\u003eWoVoGen: World Volume-Aware Diffusion for Controllable Multi-Camera Driving Scene Generation | ECCV 2024 | - | [![GitHub](https://img.shields.io/github/stars/fudan-zvg/WoVoGen)](https://github.com/fudan-zvg/WoVoGen) |\n| `Delphi` | [![arXiv](https://img.shields.io/badge/arXiv-2406.01349-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2406.01349)\u003cbr\u003eUnleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://westlake-autolab.github.io/delphi.github.io/) | [![GitHub](https://img.shields.io/github/stars/westlake-autolab/Delphi)](https://github.com/westlake-autolab/Delphi) |\n| `SimGen` | [![arXiv](https://img.shields.io/badge/arXiv-2406.09386-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2406.09386)\u003cbr\u003eSimGen: Simulator-conditioned Driving Scene Generation | NeurIPS 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://metadriverse.github.io/simgen/) | [![GitHub](https://img.shields.io/github/stars/metadriverse/SimGen)](https://github.com/metadriverse/SimGen) |\n| `BEVWorld` | [![arXiv](https://img.shields.io/badge/arXiv-2407.05679-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2407.05679)\u003cbr\u003eBEVWorld: A Multimodal World Simulator for Autonomous Driving via Scene-Level BEV Latents | arXiv 2024 | - | - |\n| `PerLDiff` | [![arXiv](https://img.shields.io/badge/arXiv-2407.06109-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2407.06109)\u003cbr\u003ePerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://perldiff.github.io/) | [![GitHub](https://img.shields.io/github/stars/LabShuHangGU/PerlDiff)](https://github.com/LabShuHangGU/PerlDiff) |\n| `Panacea+` | [![arXiv](https://img.shields.io/badge/arXiv-2408.07605-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2408.07605)\u003cbr\u003ePanacea+: Panoramic and Controllable Video Generation for Autonomous Driving | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://panacea-ad.github.io/) | - |\n| `DiVE` | [![arXiv](https://img.shields.io/badge/arXiv-2409.01595-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2409.01595)\u003cbr\u003eDiVE: DiT-Based Video Generation with Enhanced Control | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://liautoad.github.io/DIVE/) | [![GitHub](https://img.shields.io/github/stars/LiAutoAD/DIVE)](https://github.com/LiAutoAD/DIVE) |\n| `SyntheOcc` | [![arXiv](https://img.shields.io/badge/arXiv-2410.00337-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2410.00337)\u003cbr\u003eSyntheOcc: Synthesize Geometric-Controlled Street View Images through 3D Semantic MPIs | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://len-li.github.io/syntheocc-web/) | [![GitHub](https://img.shields.io/github/stars/EnVision-Research/SyntheOcc)](https://github.com/EnVision-Research/SyntheOcc) |\n| `MagicDrive-V2` | [![arXiv](https://img.shields.io/badge/arXiv-2411.13807-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2411.13807)\u003cbr\u003eMagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://gaoruiyuan.com/magicdrive-v2/) | - |\n| `HoloDrive` | [![arXiv](https://img.shields.io/badge/arXiv-2412.01407-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.01407)\u003cbr\u003eHoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving | arXiv 2024 | - | - |\n| `CogDriving` | [![arXiv](https://img.shields.io/badge/arXiv-2412.03520-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.03520)\u003cbr\u003eSeeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://luhannan.github.io/CogDrivingPage/) | - |\n| `UniMLVG` | [![arXiv](https://img.shields.io/badge/arXiv-2412.04842-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.04842)\u003cbr\u003eUniMLVG: Unified Framework for Multi-View Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving | arXiv 2024 | - | [![GitHub](https://img.shields.io/github/stars/SenseTime-FVG/OpenDWM)](https://github.com/SenseTime-FVG/OpenDWM) |\n| `DrivePhysica` | [![arXiv](https://img.shields.io/badge/arXiv-2412.08410-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.08410)\u003cbr\u003ePhysical Informed Driving World Model | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://metadrivescape.github.io/papers_project/DrivePhysica/page.html) | - |\n| `DriveDreamer-2` | [![arXiv](https://img.shields.io/badge/arXiv-2403.06845-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2403.06845)\u003cbr\u003eDriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation | AAAI 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://drivedreamer2.github.io/) | [![GitHub](https://img.shields.io/github/stars/f1yfisher/DriveDreamer2)](https://github.com/f1yfisher/DriveDreamer2) |\n| `SubjectDrive` | [![arXiv](https://img.shields.io/badge/arXiv-2403.19438-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2403.19438)\u003cbr\u003eSubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control | AAAI 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://subjectdrive.github.io/) | - |\n| `Glad` | [![arXiv](https://img.shields.io/badge/arXiv-2503.00045-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.00045)\u003cbr\u003eGlad: A Streaming Scene Generator for Autonomous Driving | ICLR 2025 | - | [![GitHub](https://img.shields.io/github/stars/xb534/Glad)](https://github.com/xb534/Glad) |\n| `DualDiff` | [![arXiv](https://img.shields.io/badge/arXiv-2505.01857-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2505.01857)\u003cbr\u003eDualDiff: Dual-Branch Diffusion Model for Autonomous Driving with Semantic Fusion | ICRA 2025 | - | [![GitHub](https://img.shields.io/github/stars/yangzhaojason/DualDiff)](https://github.com/yangzhaojason/DualDiff) |\n| `UniScene` | [![arXiv](https://img.shields.io/badge/arXiv-2412.05435-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.05435)\u003cbr\u003eUniScene: Unified Occupancy-Centric Driving Scene Generation | CVPR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://arlo0o.github.io/uniscene/) | [![GitHub](https://img.shields.io/github/stars/Arlo0o/UniScene-Unified-Occupancy-centric-Driving-Scene-Generation)](https://github.com/Arlo0o/UniScene-Unified-Occupancy-centric-Driving-Scene-Generation) |\n| `DriveScape` | [![arXiv](https://img.shields.io/badge/arXiv-2409.05463-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2409.05463)\u003cbr\u003eDriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation | CVPR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://metadrivescape.github.io/papers_project/drivescapev1/index.html) | - |\n| `Cosmos-Transfer1` | [![arXiv](https://img.shields.io/badge/arXiv-2503.14492-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.14492)\u003cbr\u003eCosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://research.nvidia.com/labs/dir/cosmos-transfer1/) | [![GitHub](https://img.shields.io/github/stars/nvidia-cosmos/cosmos-transfer1)](https://github.com/nvidia-cosmos/cosmos-transfer1) |\n| `DualDiff+` | [![arXiv](https://img.shields.io/badge/arXiv-2503.03689-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.03689)\u003cbr\u003eDualDiff+: Dual-Branch Diffusion for High-Fidelity Video Generation with Reward Guidance | arXiv 2025 | - | [![GitHub](https://img.shields.io/github/stars/yangzhaojason/DualDiff)](https://github.com/yangzhaojason/DualDiff) |\n| `CoGen` | [![arXiv](https://img.shields.io/badge/arXiv-2503.22231-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.22231)\u003cbr\u003eCoGen: 3D Consistent Video Generation via Adaptive Conditioning for Autonomous Driving | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://xiaomi-research.github.io/cogen/) | - |\n| `NoiseController` | [![arXiv](https://img.shields.io/badge/arXiv-2504.18448-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2504.18448)\u003cbr\u003eNoiseController: Towards Consistent Multi-View Video Generation via Noise Decomposition and Collaboration | arXiv 2025 | - | - |\n| `STAGE` | [![arXiv](https://img.shields.io/badge/arXiv-2506.13138-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2506.13138)\u003cbr\u003eSTAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation | arXiv 2025 | - | - |\n||\n\n\n\n### :two:\n\n\u003e :timer_clock: In chronological order, from the earliest to the latest.\n\n| Model | Paper | Venue | Website | GitHub | \n|:-:|:-|:-:|:-:|:-:|\n||\n| `GAIA-1` | [![arXiv](https://img.shields.io/badge/arXiv-2309.17080-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2309.17080)\u003cbr\u003eGAIA-1: A Generative World Model for Autonomous Driving | arXiv 2023 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://wayve.ai/thinking/scaling-gaia-1/) | - |\n| `ADriver-I` | [![arXiv](https://img.shields.io/badge/arXiv-2311.13549-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2311.13549)\u003cbr\u003eADriver-I: A General World Model for Autonomous Driving | arXiv 2023 | - | - |\n| `Drive-WM` | [![arXiv](https://img.shields.io/badge/arXiv-2311.17918-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2311.17918)\u003cbr\u003eDriving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving | CVPR 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://drive-wm.github.io/) | [![GitHub](https://img.shields.io/github/stars/BraveGroup/Drive-WM)](https://github.com/BraveGroup/Drive-WM) |\n| `DriveDreamer` | [![arXiv](https://img.shields.io/badge/arXiv-2309.09777-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2309.09777)\u003cbr\u003eDriveDreamer: Towards Real-world-driven World Models for Autonomous Driving | ECCV 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://drivedreamer.github.io/) | [![GitHub](https://img.shields.io/github/stars/JeffWang987/DriveDreamer)](https://github.com/JeffWang987/DriveDreamer) |\n| `GenAD` | [![arXiv](https://img.shields.io/badge/arXiv-2403.09630-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2403.09630)\u003cbr\u003eGenAD: Generalized Predictive Model for Autonomous Driving | ECCV 2024 | - | [![GitHub](https://img.shields.io/github/stars/OpenDriveLab/DriveAGI)](https://github.com/OpenDriveLab/DriveAGI) |\n| `Vista` | [![arXiv](https://img.shields.io/badge/arXiv-2405.17398-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2405.17398)\u003cbr\u003eVista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability | NeurIPS 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://vista-demo.github.io/) | [![GitHub](https://img.shields.io/github/stars/OpenDriveLab/Vista)](https://github.com/OpenDriveLab/Vista) |\n| `InfinityDrive` | [![arXiv](https://img.shields.io/badge/arXiv-2412.01522-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.01522)\u003cbr\u003eInfinityDrive: Breaking Time Limits in Driving World Models | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://metadrivescape.github.io/papers_project/InfinityDrive/page.html) | - |\n| `DrivingGPT` | [![arXiv](https://img.shields.io/badge/arXiv-2412.18607-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.18607)\u003cbr\u003eDrivingGPT: Unifying Driving World Modeling and Planning with Multi-Modal Autoregressive Transformers | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://rogerchern.github.io/DrivingGPT/) | - |\n| `DrivingWorld` | [![arXiv](https://img.shields.io/badge/arXiv-2412.19505-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.19505)\u003cbr\u003eDrivingWorld: Constructing World Model for Autonomous Driving via Video GPT | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://huxiaotaostasy.github.io/DrivingWorld/index.html) | [![GitHub](https://img.shields.io/github/stars/YvanYin/DrivingWorld)](https://github.com/YvanYin/DrivingWorld) |\n| `GEM` | [![arXiv](https://img.shields.io/badge/arXiv-2412.11198-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.11198)\u003cbr\u003eGEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control | CVPR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://vita-epfl.github.io/GEM.github.io/) | [![GitHub](https://img.shields.io/github/stars/vita-epfl/GEM)](https://github.com/vita-epfl/GEM) |\n| `MaskGWM` | [![arXiv](https://img.shields.io/badge/arXiv-2502.11663-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2502.11663)\u003cbr\u003eMaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction | CVPR 2025 | - | [![GitHub](https://img.shields.io/github/stars/SenseTime-FVG/OpenDWM)](https://github.com/SenseTime-FVG/OpenDWM) |\n| `VaViM \u0026 VaVAM` | [![arXiv](https://img.shields.io/badge/arXiv-2502.15672-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2502.15672)\u003cbr\u003eVaViM and VaVAM: Autonomous Driving through Video Generative Modeling | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://valeoai.github.io/vavim-vavam/) | [![GitHub](https://img.shields.io/github/stars/valeoai/VideoActionModel)](https://github.com/valeoai/VideoActionModel) |\n| `MiLA` | [![arXiv](https://img.shields.io/badge/arXiv-2503.15875-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.15875)\u003cbr\u003eMiLA: Multi-View Intensive-Fidelity Long-Term Video Generation World Model for Autonomous Driving | arXiv 2025 | - | [![GitHub](https://img.shields.io/github/stars/xiaomi-mlab/mila.github.io)](https://github.com/xiaomi-mlab/mila.github.io) |\n| `GAIA-2` | [![arXiv](https://img.shields.io/badge/arXiv-2503.20523-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.20523)\u003cbr\u003eGAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://wayve.ai/thinking/gaia-2) | - |\n| `DriVerse` | [![arXiv](https://img.shields.io/badge/arXiv-2504.18576-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2504.18576)\u003cbr\u003eDriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment | arXiv 2025 | - | - |\n| `PosePilot` | [![arXiv](https://img.shields.io/badge/arXiv-2505.01729-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2505.01729)\u003cbr\u003ePosePilot: Steering Camera Pose for Generative World Models with Self-Supervised Depth | arXiv 2025 | - | - |\n| `ProphetDWM` | [![arXiv](https://img.shields.io/badge/arXiv-2505.18650-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2505.18650)\u003cbr\u003eProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos | arXiv 2025 | - | - |\n| `GeoDrive` | [![arXiv](https://img.shields.io/badge/arXiv-2505.22421-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2505.22421)\u003cbr\u003eGeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control | arXiv 2025 | - | [![GitHub](https://img.shields.io/github/stars/antonioo-c/GeoDrive)](https://github.com/antonioo-c/GeoDrive) |\n| `LongDWM` | [![arXiv](https://img.shields.io/badge/arXiv-2506.01546-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2506.01546)\u003cbr\u003eLongDWM: Cross-Granularity Distillation for Building A Long-Term Driving World Model | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://wang-xiaodong1899.github.io/longdwm/) | [![GitHub](https://img.shields.io/github/stars/Wang-Xiaodong1899/Long-DWM)](https://github.com/Wang-Xiaodong1899/Long-DWM) |\n||\n\n\n\n## :three: Closed-Loop Simulator\n\n\u003e :timer_clock: In chronological order, from the earliest to the latest.\n\n| Model | Paper | Venue | Website | GitHub | \n|:-:|:-|:-:|:-:|:-:|\n||\n| `MagicDrive3D` | [![arXiv](https://img.shields.io/badge/arXiv-2405.14475-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2405.14475)\u003cbr\u003eMagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://gaoruiyuan.com/magicdrive3d/) | [![GitHub](https://img.shields.io/github/stars/flymin/MagicDrive3D)](https://github.com/flymin/MagicDrive3D) |\n| `DriveArena` | [![arXiv](https://img.shields.io/badge/arXiv-2408.00415-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2408.00415)\u003cbr\u003eDriveArena: A Closed-Loop Generative Simulation Platform for Autonomous Driving | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://pjlab-adg.github.io/DriveArena/) | [![GitHub](https://img.shields.io/github/stars/PJLab-ADG/DriveArena)](https://github.com/PJLab-ADG/DriveArena) |\n| `DreamForge` | [![arXiv](https://img.shields.io/badge/arXiv-2409.04003-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2409.04003)\u003cbr\u003eDreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://pjlab-adg.github.io/DriveArena/dreamforge/) | [![GitHub](https://img.shields.io/github/stars/PJLab-ADG/DriveArena)](https://github.com/PJLab-ADG/DriveArena) |\n| `InfiniCube` | [![arXiv](https://img.shields.io/badge/arXiv-2412.03934-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.03934)\u003cbr\u003eInfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://research.nvidia.com/labs/toronto-ai/infinicube/) | - |\n| `Doe-1` | [![arXiv](https://img.shields.io/badge/arXiv-2412.09627-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.09627)\u003cbr\u003eDoe-1: Closed-Loop Autonomous Driving with Large World Model | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://wzzheng.net/Doe/) | [![GitHub](https://img.shields.io/github/stars/wzzheng/Doe)](https://github.com/wzzheng/Doe) |\n| `DrivingSphere` | [![arXiv](https://img.shields.io/badge/arXiv-2411.11252-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2411.11252)\u003cbr\u003eDrivingSphere: Building A High-Fidelity 4D World for Closed-Loop Simulation | CVPR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://yanty123.github.io/DrivingSphere/) | [![GitHub](https://img.shields.io/github/stars/yanty123/DrivingSphere)](https://github.com/yanty123/DrivingSphere) |\n| `UMGen` | [![arXiv](https://img.shields.io/badge/arXiv-2503.14945-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.14945)\u003cbr\u003eGenerating Multimodal Driving Scenes via Next-Scene Prediction | CVPR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://yanhaowu.github.io/UMGen/) | [![GitHub](https://img.shields.io/github/stars/YanhaoWu/UMGen)](https://github.com/YanhaoWu/UMGen) |\n| `UniFuture` | [![arXiv](https://img.shields.io/badge/arXiv-2503.13587-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.13587)\u003cbr\u003eSeeing the Future, Perceiving the Future: A Unified Driving World Model for Future Generation and Perception | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://dk-liang.github.io/UniFuture/) | [![GitHub](https://img.shields.io/github/stars/dk-liang/UniFuture)](https://github.com/dk-liang/UniFuture) |\n| `DiST-4D` | [![arXiv](https://img.shields.io/badge/arXiv-2503.15208-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.15208)\u003cbr\u003eDiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation | arXiv 2025 | - | - |\n| `Nexus` | [![arXiv](https://img.shields.io/badge/arXiv-2504.10485-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2504.10485)\u003cbr\u003eDecoupled Diffusion Sparks Adaptive Scene Generation | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://opendrivelab.com/Nexus/) | [![GitHub](https://img.shields.io/github/stars/OpenDriveLab/Nexus)](https://github.com/OpenDriveLab/Nexus) |\n| `Challenger` | [![arXiv](https://img.shields.io/badge/arXiv-2505.15880-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2505.15880)\u003cbr\u003eChallenger: Affordable Adversarial Driving Video Generation | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://pixtella.github.io/Challenger/) | [![GitHub](https://img.shields.io/github/stars/Pixtella/Challenger)](https://github.com/Pixtella/Challenger) |\n| `Cosmos-Drive` | [![arXiv](https://img.shields.io/badge/arXiv-2506.09042-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2506.09042)\u003cbr\u003eCosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://research.nvidia.com/labs/toronto-ai/cosmos_drive_dreams/) | [![GitHub](https://img.shields.io/github/stars/nv-tlabs/Cosmos-Drive-Dreams)](https://github.com/nv-tlabs/Cosmos-Drive-Dreams) |\n||\n\n\n\n### :four: Scene Reconstructor\n\n\u003e :timer_clock: In chronological order, from the earliest to the latest.\n\n| Model | Paper | Venue | Website | GitHub | \n|:-:|:-|:-:|:-:|:-:|\n||\n| `3DGS` | [![arXiv](https://img.shields.io/badge/arXiv-2401.01339-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2401.01339)\u003cbr\u003e3D Gaussian Splatting for Real-Time Radiance Field Rendering | TOG 2023 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/) | [![GitHub](https://img.shields.io/github/stars/graphdeco-inria/gaussian-splatting)](https://github.com/graphdeco-inria/gaussian-splatting)\n| `StreetGaussian` | [![arXiv](https://img.shields.io/badge/arXiv-2401.01339-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2401.01339)\u003cbr\u003eStreet Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting | ECCV 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://zju3dv.github.io/street_gaussians) | [![GitHub](https://img.shields.io/github/stars/zju3dv/street_gaussians)](https://github.com/zju3dv/street_gaussians) |\n| `4DGF` | [![arXiv](https://img.shields.io/badge/arXiv-2406.03175-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2406.03175)\u003cbr\u003eDynamic 3D Gaussian Fields for Urban Areas | NeurIPS 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://tobiasfshr.github.io/pub/4dgf/) | [![GitHub](https://img.shields.io/github/stars/tobiasfshr/map4d)](https://github.com/tobiasfshr/map4d) |\n| `MagicDrive3D` | [![arXiv](https://img.shields.io/badge/arXiv-2405.14475-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2405.14475)\u003cbr\u003eMagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://gaoruiyuan.com/magicdrive3d/) | [![GitHub](https://img.shields.io/github/stars/flymin/MagicDrive3D)](https://github.com/flymin/MagicDrive3D) |\n| `S3Gaussian` | [![arXiv](https://img.shields.io/badge/arXiv-2405.20323-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2405.20323)\u003cbr\u003eS3Gaussian: Self-Supervised Street Gaussians for Autonomous Driving | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://wzzheng.net/S3Gaussian/) | [![GitHub](https://img.shields.io/github/stars/nnanhuang/S3Gaussian)](https://github.com/nnanhuang/S3Gaussian/) |\n| `VDG` | [![arXiv](https://img.shields.io/badge/arXiv-2406.18198-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2406.18198)\u003cbr\u003eVDG: Vision-Only Dynamic Gaussian for Driving Simulation | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://3d-aigc.github.io/VDG/) | [![GitHub](https://img.shields.io/github/stars/lifuguan/VDG_official)](https://github.com/lifuguan/VDG_official) |\n| `UniGaussian` | [![arXiv](https://img.shields.io/badge/arXiv-2411.15355-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2411.15355)\u003cbr\u003eUniGaussian: Driving Scene Reconstruction from Multiple Camera Models via Unified Gaussian Representations | arXiv 2024 |  |  |\n| `InfiniCube` | [![arXiv](https://img.shields.io/badge/arXiv-2412.03934-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.03934)\u003cbr\u003eInfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://research.nvidia.com/labs/toronto-ai/infinicube/) |  |\n| `Stag-1` | [![arXiv](https://img.shields.io/badge/arXiv-2412.05280-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.05280)\u003cbr\u003eStag-1: Towards Realistic 4D Driving Simulation with Video Generation Model | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://wzzheng.net/Stag/) | [![GitHub](https://img.shields.io/github/stars/wzzheng/Stag)](https://github.com/wzzheng/Stag) |\n| `DrivingRecon` | [![arXiv](https://img.shields.io/badge/arXiv-2412.09043-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.09043)\u003cbr\u003eDrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving | arXiv 2024 | | [![GitHub](https://img.shields.io/github/stars/EnVision-Research/DriveRecon)](https://github.com/EnVision-Research/DriveRecon) |\n| `OccScene` | [![arXiv](https://img.shields.io/badge/arXiv-2412.11183-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.11183)\u003cbr\u003eOccScene: Semantic Occupancy-Based Cross-Task Mutual Learning for 3D Scene Generation | arXiv 2024 |  | |\n| `SGD` | [![arXiv](https://img.shields.io/badge/arXiv-2403.20079-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2403.20079)\u003cbr\u003eSGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior | WACV 2025 | |  |\n| `OmniRe` | [![arXiv](https://img.shields.io/badge/arXiv-2408.16760-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2408.16760)\u003cbr\u003eOmniRe: Omni Urban Scene Reconstruction| ICLR 2025 |[![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://ziyc.github.io/omnire/) | |\n| `DriveDreamer4D` | [![arXiv](https://img.shields.io/badge/arXiv-2410.13571-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2410.13571)\u003cbr\u003eDriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation | CVPR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://drivedreamer4d.github.io/) | [![GitHub](https://img.shields.io/github/stars/GigaAI-research/DriveDreamer4D)](https://github.com/GigaAI-research/DriveDreamer4D) |\n| `DeSiRe-GS` | [![arXiv](https://img.shields.io/badge/arXiv-2411.11921-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2411.11921)\u003cbr\u003eDeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes | CVPR 2025 | | [![GitHub](https://img.shields.io/github/stars/chengweialan/DeSiRe-GS)](https://github.com/chengweialan/DeSiRe-GS) |\n| `SplatAD` | [![arXiv](https://img.shields.io/badge/arXiv-2411.16816-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2411.16816)\u003cbr\u003eSplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving | CVPR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://research.zenseact.com/publications/splatad/) | [![GitHub](https://img.shields.io/github/stars/carlinds/splatad)](https://github.com/carlinds/splatad) |\n| `ReconDreamer` | [![arXiv](https://img.shields.io/badge/arXiv-2411.19548-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2411.19548)\u003cbr\u003eReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration | CVPR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://recondreamer.github.io/) | [![GitHub](https://img.shields.io/github/stars/GigaAI-research/ReconDreamer)](https://github.com/GigaAI-research/ReconDreamer/) |\n| `FreeSim` | [![arXiv](https://img.shields.io/badge/arXiv-2412.03566-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.03566)\u003cbr\u003eFreeSim: Toward Free-Viewpoint Camera Simulation in Driving Scenes | CVPR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://drive-sim.github.io/freesim/) | |\n| `StreetCrafter` | [![arXiv](https://img.shields.io/badge/arXiv-2412.13188-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.13188)\u003cbr\u003eStreetCrafter: Street View Synthesis with Controllable Video Diffusion Models | CVPR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://zju3dv.github.io/street_crafter/) | [![GitHub](https://img.shields.io/github/stars/zju3dv/street_crafter)](https://github.com/zju3dv/street_crafter) |\n| `FlexDrive` | [![arXiv](https://img.shields.io/badge/arXiv-2502.21093-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2502.21093)\u003cbr\u003eFlexDrive: Toward Trajectory Flexibility in Driving Scene Reconstruction and Rendering | CVPR 2025 |  |  |\n| `S-NeRF++` | [![arXiv](https://img.shields.io/badge/arXiv-2402.02112-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2402.02112)\u003cbr\u003eS-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation | TPAMI 2025 |  |  |\n| `DreamDrive` | [![arXiv](https://img.shields.io/badge/arXiv-2501.00601-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2501.00601)\u003cbr\u003eDreamDrive: Generative 4D Scene Modeling from Street View Images | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://pointscoder.github.io/DreamDrive/) | |\n| `Uni-Gaussians` | [![arXiv](https://img.shields.io/badge/arXiv-2503.08317-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.08317)\u003cbr\u003eUni-Gaussians: Unifying Camera and Lidar Simulation with Gaussians for Dynamic Driving Scenarios | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://zikangyuan.github.io/UniGaussians/) | |\n| `MuDG` | [![arXiv](https://img.shields.io/badge/arXiv-2503.10604-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.10604)\u003cbr\u003eMuDG: Taming Multi-Modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction | arXiv 2025 | | [![GitHub](https://img.shields.io/github/stars/heiheishuang/MuDG)](https://github.com/heiheishuang/MuDG) |\n| `UniFuture` | [![arXiv](https://img.shields.io/badge/arXiv-2503.13587-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.13587)\u003cbr\u003eSeeing the Future, Perceiving the Future: A Unified Driving World Model for Future Generation and Perception | arXiv 2025 | |[![GitHub](https://img.shields.io/github/stars/dk-liang/UniFuture)](https://github.com/dk-liang/UniFuture)|\n| `DiST-4D` | [![arXiv](https://img.shields.io/badge/arXiv-2503.15208-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.15208)\u003cbr\u003eDisentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation | arXiv 2025 |[![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://royalmelon0505.github.io/DiST-4D/) | [![GitHub](https://img.shields.io/github/stars/royalmelon0505/dist4d)](https://github.com/royalmelon0505/dist4d) |\n| `SceneCrafter` | [![arXiv](https://img.shields.io/badge/arXiv-2503.18108-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.18108)\u003cbr\u003eUnraveling the Effects of Synthetic Data on End-to-End Autonomous Driving Humanoid Robots | arXiv 2025 |  | [![GitHub](https://img.shields.io/github/stars/cancaries/SceneCrafter)](https://github.com/cancaries/SceneCrafter) |\n| `ReconDreamer++` | [![arXiv](https://img.shields.io/badge/arXiv-2503.18438-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.18438)\u003cbr\u003eReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://recondreamer-plus.github.io/) | [![GitHub](https://img.shields.io/github/stars/GigaAI-research/ReconDreamer-Plus)](https://github.com/GigaAI-research/ReconDreamer-Plus) |\n| `RealEngine` | [![arXiv](https://img.shields.io/badge/arXiv-2505.16902-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2505.16902)\u003cbr\u003eRealEngine: Simulating Autonomous Driving in Realistic Context | arXiv 2025 | | [![GitHub](https://img.shields.io/github/stars/fudan-zvg/RealEngine)](https://github.com/fudan-zvg/RealEngine) |\n| `GeoDrive` | [![arXiv](https://img.shields.io/badge/arXiv-2505.22421-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2505.22421)\u003cbr\u003eGeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control | arXiv 2025 |  | [![GitHub](https://img.shields.io/github/stars/antonioo-c/GeoDrive)](https://github.com/antonioo-c/GeoDrive) |\n| `PseudoSimulation` | [![arXiv](https://img.shields.io/badge/arXiv-2506.04218-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2506.04218)\u003cbr\u003ePseudo-Simulation for Autonomous Driving | arXiv 2025 |  | [![GitHub](https://img.shields.io/github/stars/autonomousvision/navsim)](https://github.com/autonomousvision/navsim) |\n| `Dreamland` | [![arXiv](https://img.shields.io/badge/arXiv-2506.08006-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2506.08006)\u003cbr\u003eDreamland: Controllable World Creation with Simulator and Generative Models | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://metadriverse.github.io/dreamland/) |  |\n||\n\n\n\n# 2. World Modeling from Occupancy Generation\n\n### :one: \n\n\u003e :timer_clock: In chronological order, from the earliest to the latest.\n\n| Model | Paper | Venue | Website | GitHub | \n|:-:|:-|:-:|:-:|:-:|\n||\n| `SSD` | [![arXiv](https://img.shields.io/badge/arXiv-2301.00527-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2301.00527)\u003cbr\u003eDiffusion Probabilistic Models for Scene-Scale 3D Categorical Data | arXiv 2023 | - | [![GitHub](https://img.shields.io/github/stars/zoomin-lee/scene-scale-diffusion)](https://github.com/zoomin-lee/scene-scale-diffusion) |\n| `WoVoGen` | [![arXiv](https://img.shields.io/badge/arXiv-2312.02934-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2312.02934)\u003cbr\u003eWoVoGen: World Volume-Aware Diffusion for Controllable Multi-Camera Driving Scene Generation | ECCV 2024 | - | [![GitHub](https://img.shields.io/github/stars/fudan-zvg/WoVoGen)](https://github.com/fudan-zvg/WoVoGen) |\n| `UrbanDiff` | [![arXiv](https://img.shields.io/badge/arXiv-2403.11697-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2403.11697)\u003cbr\u003eUrban Scene Diffusion through Semantic Occupancy Map | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://metadriverse.github.io/urbandiff/) | - |\n| `DrivingSphere` | [![arXiv](https://img.shields.io/badge/arXiv-2412.03934-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.03934)\u003cbr\u003eDrivingSphere: Building A High-Fidelity 4D World for Closed-Loop Simulation | CVPR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://yanty123.github.io/DrivingSphere/) | [![GitHub](https://img.shields.io/github/stars/yanty123/DrivingSphere)](https://github.com/yanty123/DrivingSphere) |\n| `UniScene` | [![arXiv](https://img.shields.io/badge/arXiv-2412.05435-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.05435)\u003cbr\u003eUniScene: Unified Occupancy-Centric Driving Scene Generation | CVPR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://arlo0o.github.io/uniscene/) | [![GitHub](https://img.shields.io/github/stars/Arlo0o/UniScene-Unified-Occupancy-centric-Driving-Scene-Generation)](https://github.com/Arlo0o/UniScene-Unified-Occupancy-centric-Driving-Scene-Generation) |\n| `OccScene` | [![arXiv](https://img.shields.io/badge/arXiv-2412.11183-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.11183)\u003cbr\u003eOccScene: Semantic Occupancy-Based Cross-Task Mutual Learning for 3D Scene Generation | arXiv 2024 | - | - |\n| `Liu et al.` | [![arXiv](https://img.shields.io/badge/arXiv-2503.07152-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.07152)\u003cbr\u003eControllable 3D Outdoor Scene Generation via Scene Graphs | ICCV 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://yuheng.ink/project-page/control-3d-scene/) | [![GitHub](https://img.shields.io/github/stars/yuhengliu02/control-3d-scene)](https://github.com/yuhengliu02/control-3d-scene) |\n||\n\n\n\n### :two: Occupancy Forecaster\n\n\u003e :timer_clock: In chronological order, from the earliest to the latest.\n\n| Model | Paper | Venue | Website | GitHub | \n|:-:|:-|:-:|:-:|:-:|\n||\n| `Emergent-Occ` | [![arXiv](https://img.shields.io/badge/arXiv-2210.01917-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2210.01917)\u003cbr\u003eDifferentiable Raycasting for Self-supervised Occupancy Forecasting | ECCV 2022 | - | [![GitHub](https://img.shields.io/github/stars/tarashakhurana/emergent-occ-forecasting)](https://github.com/tarashakhurana/emergent-occ-forecasting) |\n| `Khurana et al.` | [![arXiv](https://img.shields.io/badge/arXiv-2302.13130-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2302.13130)\u003cbr\u003ePoint Cloud Forecasting as a Proxy for 4D Occupancy Forecasting | CVPR 2023 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://www.cs.cmu.edu/~tkhurana/ff4d/index.html) | [![GitHub](https://img.shields.io/github/stars/tarashakhurana/4d-occ-forecasting)](https://github.com/tarashakhurana/4d-occ-forecasting) |\n| `UniWorld` | [![arXiv](https://img.shields.io/badge/arXiv-2308.07234-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2308.07234)\u003cbr\u003eUniWorld: Autonomous Driving Pre-Training via World Models | arXiv 2023 | - | - |\n| `UniScene` | [![arXiv](https://img.shields.io/badge/arXiv-2305.18829-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2305.18829)\u003cbr\u003eUniScene: Multi-Camera Unified Pre-Training via 3D Scene Reconstruction for Autonomous Driving | arXiv 2023 | - | [![GitHub](https://img.shields.io/github/stars/chaytonmin/UniScene)](https://github.com/chaytonmin/UniScene) |\n| `OccWorld` | [![arXiv](https://img.shields.io/badge/arXiv-2311.16038-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2311.16038)\u003cbr\u003eOccWorld: Learning A 3D Occupancy World Model for Autonomous Driving | ECCV 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://wzzheng.net/OccWorld/) | [![GitHub](https://img.shields.io/github/stars/wzzheng/OccWorld)](https://github.com/wzzheng/OccWorld) |\n| `Cam4DOcc` | [![arXiv](https://img.shields.io/badge/arXiv-2311.17663-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2311.17663)\u003cbr\u003eCam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications | CVPR 2024 | - | [![GitHub](https://img.shields.io/github/stars/haomo-ai/Cam4DOcc)](https://github.com/haomo-ai/Cam4DOcc) |\n| `DriveWorld` | [![arXiv](https://img.shields.io/badge/arXiv-2405.04390-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2405.04390)\u003cbr\u003eDriveWorld: 4D Pre-Trained Scene Understanding via World Models for Autonomous Driving | CVPR 2024 | - | - |\n| `OccSora` | [![arXiv](https://img.shields.io/badge/arXiv-2405.20337-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2405.20337)\u003cbr\u003eOccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://wzzheng.net/OccSora/) | [![GitHub](https://img.shields.io/github/stars/wzzheng/OccWorld)](https://github.com/wzzheng/OccSora) |\n| `UnO` | [![arXiv](https://img.shields.io/badge/arXiv-2406.08691-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2406.08691)\u003cbr\u003eUnO: Unsupervised Occupancy Fields for Perception and Forecasting | CVPR 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://waabi.ai/uno/) | - |\n| `LOPR` | [![arXiv](https://img.shields.io/badge/arXiv-2407.21126-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2407.21126)\u003cbr\u003eSelf-Supervised Multi-Future Occupancy Forecasting for Autonomous Driving | arXiv 2024 | - | - |\n| `FSF-Net` | [![arXiv](https://img.shields.io/badge/arXiv-2409.15841-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2409.15841)\u003cbr\u003eFSF-Net: Enhance 4D Occupancy Forecasting with Coarse BEV Scene Flow for Autonomous Driving | arXiv 2024 | - | - |\n| `OccLLaMA` | [![arXiv](https://img.shields.io/badge/arXiv-2409.03272-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2409.03272)\u003cbr\u003eOccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving | arXiv 2024 | -| - |\n| `DOME` | [![arXiv](https://img.shields.io/badge/arXiv-2410.10429-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2410.10429)\u003cbr\u003eDOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://gusongen.github.io/DOME) | [![GitHub](https://img.shields.io/github/stars/gusongen/DOME)](https://github.com/gusongen/DOME) |\n| `GaussianAD` | [![arXiv](https://img.shields.io/badge/arXiv-2412.10371-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.10371)\u003cbr\u003eGaussianAD: Gaussian-Centric End-to-End Autonomous Driving | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://wzzheng.net/GaussianAD) | [![GitHub](https://img.shields.io/github/stars/wzzheng/GaussianAD)](https://github.com/wzzheng/GaussianAD) |\n| `DFIT-OccWorld` | [![arXiv](https://img.shields.io/badge/arXiv-2412.13772-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.13772)\u003cbr\u003eAn Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-Assisted Training | arXiv 2024 | - | - |\n| `Drive-OccWorld` | [![arXiv](https://img.shields.io/badge/arXiv-2408.14197-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2408.14197)\u003cbr\u003eDriving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving | AAAI 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://drive-occworld.github.io/) | [![GitHub](https://img.shields.io/github/stars/yuyang-cloud/Drive-OccWorld)](https://github.com/yuyang-cloud/Drive-OccWorld) |\n| `RenderWorld` | [![arXiv](https://img.shields.io/badge/arXiv-2409.11356-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2409.11356)\u003cbr\u003eRenderWorld: World Model with Self-Supervised 3D Label | ICRA 2025 | - | - |\n| `Occ-LLM` | [![arXiv](https://img.shields.io/badge/arXiv-2502.06419-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2502.06419)\u003cbr\u003eOcc-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models | ICRA 2025 | - | - |\n| `EfficientOCF` | [![arXiv](https://img.shields.io/badge/arXiv-2411.14169-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2411.14169)\u003cbr\u003eSpatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting | CVPR 2025 | - | - |\n| `DIO` | [![arXiv](https://img.shields.io/badge/arXiv-DIO-b31b1b?style=flat-square\u0026logo=arxiv)](https://openaccess.thecvf.com/content/CVPR2025/papers/Diehl_DIO_Decomposable_Implicit_4D_Occupancy-Flow_World_Model_CVPR_2025_paper.pdf)\u003cbr\u003eDIO: Decomposable Implicit 4D Occupancy-Flow World Model | CVPR 2025 | - | - |\n| `T3Former` | [![arXiv](https://img.shields.io/badge/arXiv-2503.07338-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.07338)\u003cbr\u003eTemporal Triplane Transformers as Occupancy World Models | arXiv 2025 | - | - |\n| `UniOcc` | [![arXiv](https://img.shields.io/badge/arXiv-2503.24381-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2503.24381)\u003cbr\u003eUniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://huggingface.co/datasets/tasl-lab/uniocc) | [![GitHub](https://img.shields.io/github/stars/tasl-lab/UniOcc)](https://github.com/tasl-lab/UniOcc) |\n| `COME` | [![arXiv](https://img.shields.io/badge/arXiv-2506.13260-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2506.13260)\u003cbr\u003eCOME: Adding Scene-Centric Forecasting Control to Occupancy World Model | arXiv 2025 | - | [![GitHub](https://img.shields.io/github/stars/synsin0/COME)](https://github.com/synsin0/COME) |\n||\n\n\n\n### :three: \n\n\u003e :timer_clock: In chronological order, from the earliest to the latest.\n\n| Model | Paper | Venue | Website | GitHub | \n|:-:|:-|:-:|:-:|:-:|\n||\n| `SemCity` | [![arXiv](https://img.shields.io/badge/arXiv-2403.07773-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2403.07773)\u003cbr\u003eSemCity: Semantic Scene Generation with Triplane Diffusion | CVPR 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://sglab.kaist.ac.kr/SemCity/) |[![GitHub](https://img.shields.io/github/stars/zoomin-lee/SemCity)](https://github.com/zoomin-lee/SemCity) |\n| `XCube` | [![arXiv](https://img.shields.io/badge/arXiv-2312.03806-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2312.03806)\u003cbr\u003eXCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies | CVPR 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://research.nvidia.com/labs/toronto-ai/xcube/) | [![GitHub](https://img.shields.io/github/stars/nv-tlabs/XCube)](https://github.com/nv-tlabs/XCube) |\n| `PDD` | [![arXiv](https://img.shields.io/badge/arXiv-2311.12085-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2311.12085)\u003cbr\u003ePyramid Diffusion for Fine 3D Large Scene Generation | ECCV 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://yuheng.ink/project-page/pyramid-discrete-diffusion) | [![GitHub](https://img.shields.io/github/stars/yuhengliu02/pyramid-discrete-diffusion)](https://github.com/yuhengliu02/pyramid-discrete-diffusion) |\n| `InfiniCube` | [![arXiv](https://img.shields.io/badge/arXiv-2412.03934-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.03934)\u003cbr\u003eInfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models | arXiv 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://research.nvidia.com/labs/toronto-ai/infinicube/) | - |\n| `DynamicCity` | [![arXiv](https://img.shields.io/badge/arXiv-2410.18084-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2410.18084)\u003cbr\u003eDynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes | ICLR 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://dynamic-city.github.io/) | [![GitHub](https://img.shields.io/github/stars/3DTopia/DynamicCity)](https://github.com/3DTopia/DynamicCity) |\n| `X-Scene` | [![arXiv](https://img.shields.io/badge/arXiv-2506.13558-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2506.13558)\u003cbr\u003eX-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://x-scene.github.io/) | [![GitHub](https://img.shields.io/github/stars/yuyang-cloud/X-Scene)](https://github.com/yuyang-cloud/X-Scene) |\n| `PrITTI` | [![arXiv](https://img.shields.io/badge/arXiv-2506.19117-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2506.19117)\u003cbr\u003ePrITTI: Primitive-Based Generation of Controllable and Editable 3D Semantic Scenes | arXiv 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://raniatze.github.io/pritti/) | [![GitHub](https://img.shields.io/github/stars/avg-dev/PrITTI)](https://github.com/avg-dev/PrITTI) |\n\n\n# 3. World Modeling from LiDAR Generation\n\n### :one: \n\n\u003e :timer_clock: In chronological order, from the earliest to the latest.\n\n| Model | Paper | Venue | Website | GitHub | \n|:-:|:-|:-:|:-:|:-:|\n||\n| `DUSty-GAN` | [![arXiv](https://img.shields.io/badge/arXiv-2102.11952-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2102.11952)\u003cbr\u003eLearning to Drop Points for LiDAR Scan Synthesis | IROS 2021 | \n| `LiDARGen` | [![arXiv](https://img.shields.io/badge/arXiv-2209.03954-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2209.03954)\u003cbr\u003eLearning to Generate Realistic LiDAR Point Clouds | ECCV 2022 |\n| `DUSty-GAN v2` | [![arXiv](https://img.shields.io/badge/arXiv-2210.11750-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2210.11750)\u003cbr\u003eGenerative Range Imaging for Learning Scene Priors of 3D LiDAR Data | WACV 2023 | \n| `UltraLiDAR` | [![arXiv](https://img.shields.io/badge/arXiv-2311.01448-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2311.01448)\u003cbr\u003eUltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation | CVPR 2023 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://waabi.ai/ultralidar/) |  |\n| `Copilot4D` | [![arXiv](https://img.shields.io/badge/arXiv-2311.01017-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2311.01017)\u003cbr\u003eCopilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion | ICLR 2024 | \n| `R2DM` | [![arXiv](https://img.shields.io/badge/arXiv-2309.09256-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2309.09256)\u003cbr\u003eLiDAR Data Synthesis with Denoising Diffusion Probabilistic Models | ICRA 2024 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://kazuto1011.github.io/r2dm) |  |\n| `LiDiff` | [![arXiv](https://img.shields.io/badge/arXiv-2403.13470-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2403.13470)\u003cbr\u003eScaling Diffusion Models to Real-World 3D LiDAR Scene Completion | CVPR 2024 | - | [![GitHub](https://img.shields.io/github/stars/PRBonn/LiDiff)](https://github.com/PRBonn/LiDiff) |\n| `LiDM` | [![arXiv](https://img.shields.io/badge/arXiv-2404.00815-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2404.00815)\u003cbr\u003eTowards Realistic Scene Generation with LiDAR Diffusion Models | CVPR 2024 | - |  |\n| `ViDAR` | [![arXiv](https://img.shields.io/badge/arXiv-2312.17655-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2312.17655)\u003cbr\u003eVisual Point Cloud Forecasting enables Scalable Autonomous Driving | CVPR 2024 |\n| `RangeLDM` | [![arXiv](https://img.shields.io/badge/arXiv-2403.10094-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2403.10094)\u003cbr\u003eRangeLDM: Fast Realistic LiDAR Point Cloud Generation | ECCV 2024 | \n| `Text2LiDAR` | [![arXiv](https://img.shields.io/badge/arXiv-2407.19628-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2407.19628)\u003cbr\u003eText2LiDAR: Text-Guided LiDAR Point Cloud Generation via Equirectangular Transformer | ECCV 2024 | \n| `BEVWorld` | [![arXiv](https://img.shields.io/badge/arXiv-2407.05679-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2407.05679)\u003cbr\u003eBEVWorld: A Multimodal World Simulator for Autonomous Driving via Scene-Level BEV Latents | arXiv 2024 | \n| `HoloDrive` | [![arXiv](https://img.shields.io/badge/arXiv-2412.01407-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.01407)\u003cbr\u003eHoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving | arXiv 2024 |\n| `LiDARGRIT` | [![arXiv](https://img.shields.io/badge/arXiv-2404.05505-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2404.05505)\u003cbr\u003eTaming Transformers for Realistic Lidar Point Cloud Generation | arXiv 2024 |\n| `SDS` | [![arXiv](https://img.shields.io/badge/arXiv-2410.11628-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2410.11628)\u003cbr\u003eSimultaneous Diffusion Sampling for Conditional LiDAR Generation | arXiv 2024 | \n| `OLiDM` | [![arXiv](https://img.shields.io/badge/arXiv-2412.17226-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.17226)\u003cbr\u003eOLiDM: Object-Aware LiDAR Diffusion Models for Autonomous Driving | AAAI 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://yanty123.github.io/OLiDM) |  |\n| `X-Drive` | [![arXiv](https://img.shields.io/badge/arXiv-2411.01123-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2411.01123)\u003cbr\u003eX-Drive: Cross-Modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios | ICLR 2025 | - | [![GitHub](https://img.shields.io/github/stars/yichen928/X-Drive)](https://github.com/yichen928/X-Drive) |\n| `R2Flow` | [![arXiv](https://img.shields.io/badge/arXiv-2412.02241-b31b1b?style=flat-square\u0026logo=arxiv)](https://arxiv.org/abs/2412.02241)\u003cbr\u003eFast LiDAR Data Generation with Rectified Flows | ICRA 2025 | [![Website](https://img.shields.io/badge/Link-yellow?style=flat-square\u0026logo=gitbook)](https://kazuto1011.github.io/r2flow/) | [![GitHub](https://img.shields.io/github/stars/kazuto1011/r2flow)](https://github.com/kazuto1011/r2flow) |\n| `LidarDM` |\n| `WeatherGen` |\n| `HERMES` |\n| `DriveX` |\n| `SPIRAL` |\n\n\n\n\n# 4. Datasets \u0026 Benchmarks\n\n\n\n\n# 5. Applications\n\n\n\n\n# 6. Other Resources\n\n### Workshops\n\n\n### Tutorials\n\n\n### Talks \u0026 Seminars\n\n\n\n\n# 7. Acknowledgements\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fworldbench%2Fsurvey","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fworldbench%2Fsurvey","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fworldbench%2Fsurvey/lists"}