Pi-GS: Sparse-View Gaussian Splatting with Dense π^3 Initialization
This work addresses a bottleneck in 3D reconstruction for applications like virtual reality or robotics, though it is incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of novel view synthesis in sparse-view scenarios where 3D Gaussian Splatting struggles due to reliance on accurate camera poses and point cloud initialization, achieving state-of-the-art performance on multiple datasets.
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 π^3, a reference-free point cloud estimation network. We integrate dense initialization from π^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.