HoGS：基于齐次高斯泼溅的近远物体统一重建
HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting
AI总结：
针对3DGS在远距离物体重建上的不足，提出基于齐次坐标的HoGS方法，统一重建近远物体，显著提升远距精度并保持实时渲染。
摘要：
新视角合成最近取得了令人瞩目的进展，其中3D高斯泼溅（3DGS）提供了高效的训练时间和逼真的实时渲染。然而，对笛卡尔坐标的依赖限制了3DGS在远距离物体上的性能，而这对于重建无界户外环境至关重要。我们发现，尽管齐次坐标（射影几何中的一个概念）极其简单，将其用于3DGS流程能显著提高远距离物体的渲染精度。因此，我们提出了齐次高斯泼溅（HoGS），将齐次坐标融入3DGS框架，提供一种统一表示以增强近处和远处物体的重建。HoGS通过采用射影几何原理，有效管理户外无界环境中的广阔空间位置和尺度。实验表明，HoGS在保持近处物体高质量渲染的同时，显著提高了远距离物体重建的精度，并具备快速训练速度和实时渲染能力。我们的实现可在项目页面 https://kh129.github.io/hogs/ 获取。
英文摘要：
Novel view synthesis has demonstrated impressive progress recently, with 3D Gaussian splatting (3DGS) offering efficient training time and photorealistic real-time rendering. However, reliance on Cartesian coordinates limits 3DGS's performance on distant objects, which is important for reconstructing unbounded outdoor environments. We found that, despite its ultimate simplicity, using homogeneous coordinates, a concept on the projective geometry, for the 3DGS pipeline remarkably improves the rendering accuracies of distant objects. We therefore propose Homogeneous Gaussian Splatting (HoGS) incorporating homogeneous coordinates into the 3DGS framework, providing a unified representation for enhancing near and distant objects. HoGS effectively manages both expansive spatial positions and scales particularly in outdoor unbounded environments by adopting projective geometry principles. Experiments show that HoGS significantly enhances accuracy in reconstructing distant objects while maintaining high-quality rendering of nearby objects, along with fast training speed and real-time rendering capability. Our implementations are available on our project page https://kh129.github.io/hogs/.
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。
