POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality

Joey Wilson, Marcelino Almeida, Sachit Mahajan, Martin Labrie, Maani Ghaffari, Omid Ghasemalizadeh, Min Sun, Cheng-Hao Kuo, Arnab Sen; Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), 2025, pp. 3646-3655

Abstract


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.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Wilson_2025_CVPR, author = {Wilson, Joey and Almeida, Marcelino and Mahajan, Sachit and Labrie, Martin and Ghaffari, Maani and Ghasemalizadeh, Omid and Sun, Min and Kuo, Cheng-Hao and Sen, Arnab}, title = {POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)}, month = {June}, year = {2025}, pages = {3646-3655} }