DrivingRecon：面向自动驾驶的大型4D高斯重建模型
DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving
AI总结：
针对现有自动驾驶街景4D重建方法离线、迭代耗时的问题，提出可泛化模型DrivingRecon，通过PD-Block融合环视、动静解耦增强时序信息，提升重建与新视角合成效果，并探索多场景应用。
摘要：
街景的照片级真实感4D重建对开发自动驾驶的真实世界模拟器至关重要。然而，现有大多数方法以离线方式执行该任务，且依赖耗时的迭代过程，限制了其实际应用。为此，我们提出大型4D高斯重建模型DrivingRecon，这是一种可泛化的驾驶场景重建模型，可直接从环视视频预测4D高斯。为更好地融合环视图像，我们提出剪枝与膨胀模块（PD-Block），用于消除相邻视图间的重叠高斯点并去除冗余背景点。为增强跨时序信息，我们定制了动静解耦策略，以更好地学习几何与运动特征。实验结果表明，与现有方法相比，DrivingRecon显著提升了场景重建质量和新视角合成效果。此外，我们还探索了DrivingRecon在模型预训练、车辆适配和场景编辑中的应用。我们的代码可在https://github.com/EnVision-Research/DriveRecon 获取。
英文摘要：
Photorealistic 4D reconstruction of street scenes is essential for developing real-world simulators in autonomous driving. However, most existing methods perform this task offline and rely on time-consuming iterative processes, limiting their practical applications. To this end, we introduce the Large 4D Gaussian Reconstruction Model (DrivingRecon), a generalizable driving scene reconstruction model, which directly predicts 4D Gaussian from surround view videos. To better integrate the surround-view images, the Prune and Dilate Block (PD-Block) is proposed to eliminate overlapping Gaussian points between adjacent views and remove redundant background points. To enhance cross-temporal information, dynamic and static decoupling is tailored to better learn geometry and motion features. Experimental results demonstrate that DrivingRecon significantly improves scene reconstruction quality and novel view synthesis compared to existing methods. Furthermore, we explore applications of DrivingRecon in model pre-training, vehicle adaptation, and scene editing. Our code is available at https://github.com/EnVision-Research/DriveRecon.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
