ArmGS: Composite Gaussian Appearance Refinement for Modeling Dynamic Urban Environments
This work addresses the need for high-fidelity, real-time rendering in autonomous driving simulation, representing an incremental improvement over existing 3D Gaussian splatting approaches.
The paper tackles the problem of modeling dynamic urban environments for autonomous driving simulation by proposing ArmGS, a method using composite Gaussian splatting with multi-granularity appearance refinement, which achieves superior performance over state-of-the-art methods on multiple challenging datasets including Waymo, KITTI, NOTR, and VKITTI2.
This work focuses on modeling dynamic urban environments for autonomous driving simulation. Contemporary data-driven methods using neural radiance fields have achieved photorealistic driving scene modeling, but they suffer from low rendering efficacy. Recently, some approaches have explored 3D Gaussian splatting for modeling dynamic urban scenes, enabling high-fidelity reconstruction and real-time rendering. However, these approaches often neglect to model fine-grained variations between frames and camera viewpoints, leading to suboptimal results. In this work, we propose a new approach named ArmGS that exploits composite driving Gaussian splatting with multi-granularity appearance refinement for autonomous driving scene modeling. The core idea of our approach is devising a multi-level appearance modeling scheme to optimize a set of transformation parameters for composite Gaussian refinement from multiple granularities, ranging from local Gaussian level to global image level and dynamic actor level. This not only models global scene appearance variations between frames and camera viewpoints, but also models local fine-grained changes of background and objects. Extensive experiments on multiple challenging autonomous driving datasets, namely, Waymo, KITTI, NOTR and VKITTI2, demonstrate the superiority of our approach over the state-of-the-art methods.