In this paper, we present 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 small number of
images are available. To address this issue, we introduce a dense depth map as
a geometry guide to mitigate overfitting. We obtained the depth map using a
pre-trained monocular depth estimation model and aligning the scale and offset
using sparse COLMAP feature points. The adjusted depth aids in the color-based
optimization of 3D Gaussian splatting, mitigating floating artifacts, and
ensuring adherence to geometric constraints. We verify the proposed method on
the NeRF-LLFF dataset with varying numbers of few images. Our approach
demonstrates robust geometry compared to the original method that relies solely
on images.

通过引入密集深度图，用于减轻过拟合问题，我们提出了一种方法来优化具有有限图像数量的高斯喷洒。我们通过将众多高斯喷溅结合起来表示 3D 场景，取得了出色的视觉效果。我们使用预训练的单目深度估计模型获取深度图，然后通过稀疏 COLMAP 特征点对其进行缩放和偏移的调整。调整后的深度图有助于基于颜色的 3D 高斯喷溅优化，减轻浮动伪影并确保符合几何约束。我们在具有不同数量的少量图像的 NeRF-LLFF 数据集上验证了该方法，与仅依赖图像的原始方法相比，我们的方法展示了稳健的几何性能。