Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field
This work addresses the need for reliable uncertainty quantification in 3DGS-based active mapping, a key problem for robotics and autonomous navigation.
GAVIS introduces a principled method for uncertainty quantification in 3D Gaussian Splatting by modeling anisotropic visibility fields, enabling real-time (200 FPS) uncertainty estimation and active mapping that consistently outperforms prior approaches in accuracy and efficiency.
We present Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel framework for uncertainty quantification and active mapping in 3DGS. Our key insight is that regions unseen from the training views yield unreliable predictions from the 3DGS. To address this, we introduce a principled and efficient method for quantifying the visibility field in 3DGS, defined as the anisotropic visibility of each particle with respect to the training views, and represented using spherical harmonics. The resulting visibility field is integrated into a Bayesian Network-based uncertainty-aware 3DGS rasterizer, enabling real-time (200 FPS) uncertainty quantification for synthesized views. Active mapping is further performed within a maximum information gain framework building on this formulation. Extensive experiments across diverse environments demonstrate that GAVIS consistently and significantly outperforms prior approaches in both accuracy and efficiency. Moreover, beyond standalone use, our method can be applied post-hoc to improve the performance of existing approaches.