3D Gaussian Splatting has emerged as an efficient photorealistic novel view synthesis method. However, its reliance on sparse Structure-from-Motion (SfM) point clouds often limits scene reconstruction quality. To address the limitation, this paper proposes a novel 3D reconstruction framework, Gaussian Processes enhanced Gaussian Splatting (GP-GS), in which a multi-output Gaussian Process model is developed to enable adaptive and uncertainty-guided densification of sparse SfM point clouds. Specifically, we propose a dynamic sampling and filtering pipeline that adaptively expands the SfM point clouds by leveraging GP-based predictions to infer new candidate points from the input 2D pixels and depth maps. The pipeline utilizes uncertainty estimates to guide the pruning of high-variance predictions, ensuring geometric consistency and enabling the generation of dense point clouds. These densified point clouds provide high-quality initial 3D Gaussians, enhancing reconstruction performance. Extensive experiments conducted on synthetic and real-world datasets across various scales validate the effectiveness and practicality of the proposed framework.
View on arXiv@article{guo2025_2502.02283,
title={ GP-GS: Gaussian Processes for Enhanced Gaussian Splatting },
author={ Zhihao Guo and Jingxuan Su and Shenglin Wang and Jinlong Fan and Jing Zhang and Wei Zhou and Hadi Amirpour and Yunlong Zhao and Liangxiu Han and Peng Wang },
journal={arXiv preprint arXiv:2502.02283},
year={ 2025 }
}