Realistic scene reconstruction and view synthesis are essential for advancing autonomous driving systems by simulating safety-critical scenarios. 3D Gaussian Splatting excels in real-time rendering and static scene reconstructions but struggles with modeling driving scenarios due to complex backgrounds, dynamic objects, and sparse views. We propose AutoSplat, a framework employing Gaussian splatting to achieve highly realistic reconstructions of autonomous driving scenes. By imposing geometric constraints on Gaussians representing the road and sky regions, our method enables multi-view consistent simulation of challenging scenarios including lane changes. Leveraging 3D templates, we introduce a reflected Gaussian consistency constraint to supervise both the visible and unseen side of foreground objects. Moreover, to model the dynamic appearance of foreground objects, we estimate residual spherical harmonics for each foreground Gaussian. Extensive experiments on Pandaset and KITTI demonstrate that AutoSplat outperforms state-of-the-art methods in scene reconstruction and novel view synthesis across diverse driving scenarios. Visit our project page at https://autosplat.github.io/.
Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes
Department of Civil and Environmental Engineering, Rensselaer Polytechnic Institute（拉特克利夫理工学院土木与环境工程系）；Department of Computer and Information Sciences, University of Delaware（德雷塞尔大学计算机与信息科学系）
AD-GS: Object-Aware B-Spline Gaussian Splatting for Self-Supervised Autonomous Driving
College of Computer Science, Nankai University（南开大学计算机科学学院）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）
ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstruction
Tuojing Intelligence；The University of Hong Kong（香港大学）；King's College London（伦敦国王学院）；The University of Sydney（悉尼大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
OG-Gaussian: Occupancy Based Street Gaussians for Autonomous Driving
School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；School of Artificial Intelligence and Data Science, University of Science and Technology of China（中国科学技术大学人工智能与数据科学学院）
RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos
Sun Yat-sen University（中山大学）；Guangdong Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（教育部机器智能与先进计算重点实验室）
SuperOcc: Toward Cohesive Temporal Modeling for Superquadric-based 3D Occupancy Prediction
School of Control Science and Engineering, Dalian University of Technology, Dalian 116024, China（大连理工大学控制科学与工程学院，大连 116024，中国）；Dalian Rail Transmit Intelligent Control and Intelligent Operation Technology Innovation Center, Dalian 116024, China（大连铁路传输智能控制与智能运维技术创新中心，大连 116024，中国）；Dalian Seasky Automation Co., Ltd, Dalian 116024, China（大连海 sky 自动化有限公司，大连 116024，中国）
Physics-Aware 3D Gaussian Editing for Driving Scene Generation
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University（吉林大学汽车底盘集成与生物力学国家重点实验室）；China FAW Group Co., Ltd.（中国第一汽车集团有限公司）
CE-NPBG: Connectivity Enhanced Neural Point-Based Graphics for Novel View Synthesis in Autonomous Driving Scenes
Computer Vision Center (CVC), Universitat Autònoma de Barcelona（计算机视觉中心（CVC），巴塞罗那自治大学）；Intelligent Simulation Innovation Lab, Huawei Munich Research Center（智能仿真创新实验室，华为慕尼黑研究中心）
University of Tübingen, Tübingen AI Center（图宾根大学，图宾根人工智能中心）；NVIDIA Research（NVIDIA研究）；Robert Bosch GmbH（罗伯特·博世集团）；OpenDriveLab at Shanghai Innovation Institute（上海创新研究院自动驾驶实验室）；University of Stuttgart（斯图加特大学）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Stanford University（斯坦福大学）
VGD: Visual Geometry Gaussian Splatting for Feed-Forward Surround-view Driving Reconstruction
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology（广东省超高清沉浸媒体技术重点实验室）；School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）；Peng Cheng Laboratory（鹏城实验室）
CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splatting
Institute for AI Industry Research (AIR), Tsinghua University（人工智能产业研究院（AIR），清华大学）；Beijing Institute of Technology（北京理工大学）；Nanyang Technological University（南洋理工大学）；Tsinghua University（清华大学）；Renmin University of China（中国人民大学）；Beijing University of Technology（北京理工大学）；Baidu Inc（百度公司）；Peking University（北京大学）；Shanghai AI Lab（上海人工智能实验室）；Westlake University（西湖大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）
提出 CRUISE 框架，利用分解式 Gaussian Splatting 重建并编辑 V2X 场景，实现多视角数据增强，提升协同 3D 检测、跟踪及边角案例生成能力。
