TVG-SLAM: Robust Gaussian Splatting SLAM With Tri-View Geometric Constraints

Abstract

Recent advances in 3D Gaussian Splatting (3DGS) have enabled RGB-only SLAM systems to achieve high-fidelity scene representation. However, the heavy reliance of existing systems on photometric rendering loss for camera tracking undermines their robustness, especially in unbounded outdoor environments with severe viewpoint and illumination changes. To address these challenges, we propose TVG-SLAM, a robust RGB-only 3DGS SLAM system that leverages a novel tri-view geometry paradigm to ensure consistent tracking and high-quality mapping. We establish temporally consistent tri-view correspondences to enable three core contributions. First, Hybrid Geometric Constraints combine geometric cues (trifocal and 3D alignment) with photometric supervision, ensuring stable pose estimation when illumination shifts cause rendering inconsistencies. Second, TUGI estimates uncertainty from multi-view 3D geometric consistency-capturing cross-view stability rather than pairwise 2D matching confidence-to guide principled Gaussian initialization. Third, DART adaptively attenuates photometric trust when rendering degrades, allowing geometric priors to govern optimization. Experiments on multiple public outdoor datasets show that TVG-SLAM outperforms prior RGB-only 3DGS-based SLAM systems. Notably, in the most challenging dataset, our method reduces the average ATE by 69.0% while achieving state-of-the-art rendering quality.