GP-GS: Gaussian Processes for Enhanced Gaussian Splatting
This addresses scene reconstruction quality issues in novel view synthesis for 3D computer vision applications, representing an incremental improvement.
The paper tackles the limitation of 3D Gaussian Splatting's reliance on sparse Structure-from-Motion point clouds by proposing GP-GS, a framework that uses Gaussian Processes to adaptively densify these point clouds, enhancing reconstruction performance as validated on synthetic and real-world datasets.
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.