OmniGS：使用全方位高斯泼溅的快速辐射场重建
OmniGS: Fast Radiance Field Reconstruction using Omnidirectional Gaussian Splatting
AI总结：
提出OmniGS系统，通过理论分析球面相机导数并实现GPU加速全方位光栅化器，直接对等距柱状图像进行3D高斯溅射，实现快速高质量的全方位辐射场重建。
摘要：
依赖3D高斯泼溅（3D Gaussian Splatting）的逼真重建在多个领域展现出巨大潜力。然而，当前的3D高斯泼溅系统仅支持使用无畸变的透视图像进行辐射场重建。本文提出OmniGS，一种新颖的全方位高斯泼溅系统，利用全方位图像实现快速辐射场重建。具体而言，我们对3D高斯泼溅中的球面相机模型导数进行了理论分析。根据这些导数，我们实现了一个新的GPU加速全方位光栅化器，直接将3D高斯溅射到等距柱状屏幕空间，用于全方位图像渲染。我们实现了全方位辐射场的可微优化，无需立方体贴图校正或切平面近似。在自我中心和漫游场景中进行的大量实验表明，我们的方法在使用全方位图像时达到了最先进的重建质量和高渲染速度。代码将公开提供。
英文摘要：
Photorealistic reconstruction relying on 3D Gaussian Splatting has shown promising potential in various domains. However, the current 3D Gaussian Splatting system only supports radiance field reconstruction using undistorted perspective images. In this paper, we present OmniGS, a novel omnidirectional Gaussian splatting system, to take advantage of omnidirectional images for fast radiance field reconstruction. Specifically, we conduct a theoretical analysis of spherical camera model derivatives in 3D Gaussian Splatting. According to the derivatives, we then implement a new GPU-accelerated omnidirectional rasterizer that directly splats 3D Gaussians onto the equirectangular screen space for omnidirectional image rendering. We realize differentiable optimization of the omnidirectional radiance field without the requirement of cube-map rectification or tangent-plane approximation. Extensive experiments conducted in egocentric and roaming scenarios demonstrate that our method achieves state-of-the-art reconstruction quality and high rendering speed using omnidirectional images. The code will be publicly available.
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。
