Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

ArmGS: Composite Gaussian Appearance Refinement for Modeling Dynamic Urban Environments

About

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.

Guile Wu, Dongfeng Bai, Bingbing Liu• 2025

Related benchmarks

TaskDatasetResultRank
Novel View SynthesisWaymo
PSNR35.7
7
Novel View SynthesisKITTI
PSNR30.3
7
Image ReconstructionWaymo
PSNR38.1
6
Novel View SynthesisVKITTI2
PSNR31.1
5
Scene ReconstructionNOTR static-32
PSNR30.5
4
Scene ReconstructionNOTR (dynamic-32)
PSNR30.5
3
Showing 6 of 6 rows

Other info

Follow for update