Sparse2DGS：使用稠密点云和2D高斯泼溅的稀疏视角表面重建
Sparse2DGS: Sparse-View Surface Reconstruction using 2D Gaussian Splatting with Dense Point Cloud
AI总结：
提出Sparse2DGS方法，利用DUSt3R和COLMAP MVS生成稠密点云初始化2D高斯，解决了稀疏视角下高斯基元初始化不足的问题，仅用三张图像即可实现高精度3D表面重建。
摘要：
高斯泼溅（GS）作为一种快速有效的新视角合成方法备受关注。它也被应用于使用多视角图像进行3D重建，并能实现快速且准确的3D重建。然而，GS假设输入包含大量多视角图像，因此当仅有有限数量的输入图像可用时，重建精度会显著下降。主要原因之一是通过运动恢复结构（SfM）获得的稀疏点云中3D点数量不足，导致高斯基元优化的初始化效果较差。我们提出了一种名为Sparse2DGS的3D重建新方法，以增强2DGS仅使用三张图像重建物体的能力。Sparse2DGS采用立体图像基础模型DUSt3R结合COLMAP MVS生成高精度且稠密的3D点云，用于初始化2D高斯。在DTU数据集上的实验表明，Sparse2DGS仅用三张图像即可准确重建物体的3D形状。项目页面位于https://gsisaoki.github.io/SPARSE2DGS/
英文摘要：
Gaussian Splatting (GS) has gained attention as a fast and effective method for novel view synthesis. It has also been applied to 3D reconstruction using multi-view images and can achieve fast and accurate 3D reconstruction. However, GS assumes that the input contains a large number of multi-view images, and therefore, the reconstruction accuracy significantly decreases when only a limited number of input images are available. One of the main reasons is the insufficient number of 3D points in the sparse point cloud obtained through Structure from Motion (SfM), which results in a poor initialization for optimizing the Gaussian primitives. We propose a new 3D reconstruction method, called Sparse2DGS, to enhance 2DGS in reconstructing objects using only three images. Sparse2DGS employs DUSt3R, a fundamental model for stereo images, along with COLMAP MVS to generate highly accurate and dense 3D point clouds, which are then used to initialize 2D Gaussians. Through experiments on the DTU dataset, we show that Sparse2DGS can accurately reconstruct the 3D shapes of objects using just three images. The project page is available at https://gsisaoki.github.io/SPARSE2DGS/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
