Pi-GS: Sparse-View Gaussian Splatting with Dense π³ Initialization

Novel view synthesis has evolved rapidly, advancing from Neural Radiance Fields to 3D Gaussian Splatting (3DGS), which offers real-time rendering and rapid training without compromising visual fidelity. However, 3DGS relies heavily on accurate camera poses and high-quality point cloud initialization, which are difficult to obtain in sparse-view scenarios. While traditional Structure from Motion (SfM) pipelines often fail in these settings, existing learning-based point estimation alternatives typically require reliable reference views and remain sensitive to pose or depth errors.

In this work, we propose a robust method utilizing $\pi^3$, a reference-free point cloud estimation network. We integrate dense initialization from $\pi^3$ with a regularization scheme designed to mitigate geometric inaccuracies. Specifically, we employ uncertainty-guided depth supervision, normal consistency loss, and depth warping. Experimental results demonstrate that our approach achieves state-of-the-art performance on the Tanks and Temples, LLFF, DTU, and MipNeRF360 datasets.

Recommended citation: Manuel Hofer, Markus Steinberger, Thomas Köhler (2026). "Pi-GS: Sparse-View Gaussian Splatting with Dense π³ Initialization." In Proceedings of the 29th Computer Vision Winter Workshop (CVWW).
Download Paper