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

2025-10-26

AI Summary

Under composite degradations such as noise and low illumination, existing 3D Gaussian Splatting (3DGS)-SLAM systems suffer significant performance degradation. To address this, we propose a robust SLAM framework built upon 3D Gaussian lattices. Our key contributions are: (1) a structure-preserving multimodal robust fusion mechanism that jointly optimizes rendered appearance, depth, and edge-based geometric cues; (2) an adaptive tracking objective regularized by residual-balanced constraints to enhance pose estimation stability; and (3) a CLIP-driven semantic restoration module leveraging contrastive language–image priors to improve semantic and structural fidelity under severe degradation. Exploiting the implicit low-pass filtering property of 3DGS, our method synergistically enhances perceptual robustness and mapping accuracy. Extensive evaluations on Replica, TUM RGB-D, and real-world low-light sequences demonstrate substantial improvements over state-of-the-art 3DGS-SLAM methods in both trajectory accuracy and reconstruction quality.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: 3D Computer Vision
• Natural Language Processing: Safety and Robustness

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Enhancing SLAM robustness in noisy low-light environments
• Overcoming 3DGS vulnerability to compounded visual degradations
• Improving mapping and tracking under adverse imaging conditions

Innovation

• SP-RoFusion mechanism integrates appearance, depth, and edge cues
• Adaptive tracking objective with residual balancing regularization
• CLIP-based enhancement module restores semantic and structural fidelity