GSPotential: Camera Potential Field for Sparse-View 3D Gaussian Splatting
Computer Vision and Pattern Recognition
Summary
The authors address problems in 3D Gaussian Splatting, a method for creating realistic 3D images, which struggles when there are few camera views available. They identify areas where there is little information (called supervision valleys) and use a Camera Potential Field to find these weak spots. By placing virtual cameras strategically and carefully updating the 3D model in those areas, their approach improves the reconstruction quality without slowing down training too much. Their method helps make better 3D models even when data is sparse.
Authors
Zeyuan An, Yanghang Xiao, Zhiying Leng, Yijun Feng, Xiaohui Liang
Abstract
3D Gaussian Splatting has achieved remarkable success in photorealistic rendering, yet it suffers from severe overfitting and geometric artifacts in sparse-view scenarios due to the inherent deficiency of photometric supervision. Recent advances have attempted to regularize optimization by incorporating external priors, such as depth, point clouds, or diffusion models. However, these methods typically overlook the non-uniform distribution of supervision across the viewing space, resulting in limited specificity in prior use and primitive control. In this paper, we propose GSPotential, a framework that quantifies view-space supervision imbalance using a Camera Potential Field. Our key insight is to identify supervision valleys where photometric constraints are most deficient, and use the potential field to guide reconstruction from two complementary aspects. First, we devise a probabilistic spherical sampling strategy that places informative virtual cameras in low-potential regions. Point-cloud renderings from these views then provide targeted geometric guidance. Second, the same field provides a directional coverage cue for conservative Gaussian updates in weakly covered spatial sectors. Extensive experiments demonstrate that GSPotential achieves high reconstruction fidelity while maintaining competitive training efficiency.