RoGER-SLAM: A Robust Gaussian Splatting SLAM System for Noisy and Low-light Environment Resilience

Abstract--The reliability of Simultaneous Localization and Mapping (SLAM) is severely constrained in environments where visual inputs suffer from noise and low illumination. Although recent 3D Gaussian Splatting (3DGS) based SLAM frameworks achieve high-fidelity mapping under clean conditions, they remain vulnerable to compounded degradations that degrade mapping and tracking performance. A key observation underlying our work is that the original 3DGS rendering pipeline inherently behaves as an implicit low-pass filter, attenuating high-frequency noise but also risking over-smoothing. Building on this insight, we propose RoGER-SLAM, a robust 3DGS SLAM system tailored for noise and low-light resilience. The framework integrates three innovations: a Structure-Preserving Robust Fusion (SP-RoFusion) mechanism that couples rendered appearance, depth, and edge cues; an adaptive tracking objective with residual balancing regularization; and a Contrastive Language-Image Pretraining (CLIP)-based enhancement module, selectively activated under compounded degradations to restore semantic and structural fidelity. Comprehensive experiments on Replica, TUM, and real-world sequences show that RoGER-SLAM consistently improves trajectory accuracy and reconstruction quality compared with other 3DGS-SLAM systems, especially under adverse imaging conditions. IMUL T ANEOUS Localization and Mapping (SLAM) persists as a foundational capability for autonomous systems operating in unstructured environments, with mission-critical applications in robotics, augmented reality, and autonomous driving. With the advancement of SLAM research, the focus has gradually shifted beyond localization accuracy toward achieving photorealistic and structurally consistent map reconstruction. In this context, neural rendering techniques such as Neural Radiance Fields (NeRF) [1] have demonstrated impressive photorealistic reconstruction capabilities by representing scenes as continuous volumetric fields. However, NeRF-based SLAM approaches [2], [3], [4], [5], [6], [7] often suffer from high computational cost, slow convergence and weak structural regularization, which limit their applicability in real-time and degraded scenarios. This work was supported by the National Natural Science Foundation of China under Grant No. 62433014 and No.62133011.