Photorealistic 3D scene reconstruction plays an important role in autonomous driving, enabling the generation of novel data from existing datasets to simulate safety-critical scenarios and expand training data without additional acquisition costs. Gaussian Splatting (GS) facilitates real-time, photorealistic rendering with an explicit 3D Gaussian representation of the scene, providing faster processing and more intuitive scene editing than the implicit Neural Radiance Fields (NeRFs). While extensive GS research has yielded promising advancements in autonomous driving applications, they overlook two critical aspects: First, existing methods mainly focus on low-speed and feature-rich urban scenes and ignore the fact that highway scenarios play a significant role in autonomous driving. Second, while LiDARs are commonplace in autonomous driving platforms, existing methods learn primarily from images and use LiDAR only for initial estimates or without precise sensor modeling, thus missing out on leveraging the rich depth information LiDAR offers and limiting the ability to synthesize LiDAR data. In this paper, we propose a novel GS method for dynamic scene synthesis and editing with improved scene reconstruction through LiDAR supervision and support for LiDAR rendering. Unlike prior works that are tested mostly on urban datasets, to the best of our knowledge, we are the first to focus on the more challenging and highly relevant highway scenes for autonomous driving, with sparse sensor views and monotone backgrounds.
逼真的3D场景重建在自动驾驶中具有重要作用，它能够从现有数据集中生成新的数据，用于模拟安全关键场景，扩展训练数据，而无需额外的采集成本。Gaussian Splatting (GS) 提供了一种显式3D高斯表示的场景重建方法，实现了实时的逼真渲染，与隐式的神经辐射场（NeRFs）相比，具有更快的处理速度和更直观的场景编辑能力。 尽管现有的GS研究在自动驾驶应用中取得了显著进展，但它们忽视了两个关键问题：首先，现有方法主要关注低速和特征丰富的城市场景，而忽略了高速公路场景在自动驾驶中的重要性；其次，尽管激光雷达在自动驾驶平台中十分普遍，但现有方法主要依赖图像进行学习，仅将激光雷达数据用于初始估计或未进行精确的传感器建模，未能充分利用激光雷达丰富的深度信息，这限制了生成激光雷达数据的能力。 为解决这些问题，本文提出了一种新颖的GS方法，用于动态场景的合成和编辑。通过激光雷达监督改进场景重建，并支持激光雷达渲染。与以往主要在城市数据集上测试的工作不同，据我们所知，这是首个关注高速公路场景的研究，这类场景对自动驾驶尤为重要，但具有稀疏的传感器视角和单调的背景，挑战性更大。