Spectral GS-SLAM: Observability-Aware, Degeneracy-Robust Tracking for Real-Time 3D Gaussian Splatting SLAM

2026-06-19

AI Summary

This work addresses the instability of existing 3D Gaussian splatting-based SLAM systems in textureless or geometrically degenerate scenes, where feature matching fails and ICP optimization becomes ill-posed. To overcome this limitation, we propose an observability-aware, degradation-robust tracking framework that fuses ICP with feature constraints through adaptive compensation along under-constrained directions. Our approach introduces a Gaussian covariance-driven planarity weighting mechanism to guide information fusion without interfering with the shared Gaussian map representation. Evaluated on the TUM RGB-D benchmark sequences, the method achieves real-time performance at 40.14 FPS, maintains trajectory consistency in unstructured and textureless environments, and preserves high accuracy in conventional scenes.

Abstract

Recent 3DGS-SLAM systems enable real-time operation by leveraging conventional feature matching or ICP-based tracking, thereby avoiding the heavy dense photometric optimization used in earlier approaches. However, feature matching remains prone to failure in textureless environments, while ICP-based tracking struggles in structureless or geometrically degenerate scenes due to ill-conditioned optimization. To address this issue, we propose Spectral GS-SLAM, an efficient yet robust tracking framework that integrates ICP with complementary feature-based constraints. Our method mitigates numerical instability by adaptively compensating under-constrained directions in degenerate scenarios, without interfering with the shared Gaussian representation used for mapping. We further introduce a Gaussian-aware planarity weighting mechanism that exploits the intrinsic covariance structure of 3D Gaussians to characterize scene geometry and guide information fusion. Extensive evaluations on challenging TUM RGB-D sequences demonstrate that Spectral GS-SLAM achieves real-time performance (40.14 FPS) while maintaining consistent tracking in both structureless and featureless environments. The proposed method preserves trajectory integrity in degenerate scenes while maintaining competitive performance in non-adverse conditions.

Problem

• 3D Gaussian Splatting
• SLAM
• degeneracy
• featureless environments
• structureless scenes

Innovation

• Gaussian Splatting
• Degeneracy-Robust Tracking
• Observability-Aware Optimization
• Planarity Weighting
• Real-Time SLAM