POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality
This addresses a challenge in 3D-GS for real-world applications by providing uncertainty quantification, though it is incremental as it adapts classical methods to a new context.
The paper tackles the problem of quantifying uncertainty and information gain in 3D Gaussian Splatting (3D-GS) for applications like SLAM, by reformulating it through optimal experimental design, resulting in T-Optimality and D-Optimality performing best on two datasets.
In this paper, we present a novel algorithm for quantifying uncertainty and information gained within 3D Gaussian Splatting (3D-GS) through P-Optimality. While 3D-GS has proven to be a useful world model with high-quality rasterizations, it does not natively quantify uncertainty or information, posing a challenge for real-world applications such as 3D-GS SLAM. We propose to quantify information gain in 3D-GS by reformulating the problem through the lens of optimal experimental design, which is a classical solution widely used in literature. By restructuring information quantification of 3D-GS through optimal experimental design, we arrive at multiple solutions, of which T-Optimality and D-Optimality perform the best quantitatively and qualitatively as measured on two popular datasets. Additionally, we propose a block diagonal covariance approximation which provides a measure of correlation at the expense of a greater computation cost.