Search papers, labs, and topics across Lattice.
This paper introduces Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel method for uncertainty quantification in 3D Gaussian Splatting by modeling anisotropic visibility using spherical harmonics. GAVIS integrates this visibility field into a Bayesian Network-based rasterizer, enabling real-time uncertainty estimation for novel views. Experiments show GAVIS outperforms existing methods in accuracy and efficiency for active mapping, and can be applied post-hoc to improve other approaches.
Real-time uncertainty quantification in 3D Gaussian Splatting is now possible, unlocking more robust active mapping and view synthesis.
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.
