ArmGS: Composite Gaussian Appearance Refinement for Modeling Dynamic Urban Environments

TL;DR

ArmGS introduces a multi-granularity appearance refinement method using composite Gaussian splatting to improve dynamic urban scene modeling for autonomous driving, achieving higher fidelity and efficiency.

Contribution

It proposes a novel multi-level appearance modeling scheme with composite Gaussian refinement for better dynamic scene representation.

Findings

Outperforms state-of-the-art methods on multiple datasets

Models both global and local appearance variations

Enables high-fidelity real-time scene rendering

Abstract

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.