Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images

Abstract

This paper presents a method to optimize Gaussian splatting with a limited number of images while avoiding overfitting. Representing a 3D scene by combining numerous Gaussian splats has yielded outstanding visual quality. However, it tends to overfit the training views when only a few images are available. To address this issue, we employ an adjusted depth map as a geometric reference, derived from a pre-trained monocular depth estimation model and subsequently aligned with the sparse structure-from-motion points. We regularize the optimization process of 3D Gaussian splatting with the adjusted depth and an additional unsupervised smooth constraint, thereby effectively reducing the occurrence of floating artifacts. Our method is mainly validated on the NeRF-LLFF dataset with varying numbers of images, and we conduct multiple experiments with randomly selected training images, presenting the average value to ensure fairness. Our approach demonstrates robust geometry compared to the original method, which relied solely on images.