The rapid growth of 3D Gaussian Splatting (3DGS) has revolutionized neural
rendering, enabling real-time production of high-quality renderings. However,
the previous 3DGS-based methods have limitations in urban scenes due to
reliance on initial Structure-from-Motion(SfM) points and difficulties in
rendering distant, sky and low-texture areas. To overcome these challenges, we
propose a hybrid optimization method named HO-Gaussian, which combines a
grid-based volume with the 3DGS pipeline. HO-Gaussian eliminates the dependency
on SfM point initialization, allowing for rendering of urban scenes, and
incorporates the Point Densitification to enhance rendering quality in
problematic regions during training. Furthermore, we introduce Gaussian
Direction Encoding as an alternative for spherical harmonics in the rendering
pipeline, which enables view-dependent color representation. To account for
multi-camera systems, we introduce neural warping to enhance object consistency
across different cameras. Experimental results on widely used autonomous
driving datasets demonstrate that HO-Gaussian achieves photo-realistic
rendering in real-time on multi-camera urban datasets.

通过将网格体积与 3D 高斯喷洒（3DGS）管道结合，提出了一种名为 HO-Gaussian 的混合优化方法，以克服使用初始结构运动（SfM）点的依赖性，从而使得在城市场景中进行渲染成为可能，并且引入了点密度化来提高在训练期间出现问题的区域的渲染质量。此外，我们引入了高斯方向编码作为渲染管道中球面调和的替代方法，从而实现了视角相关的颜色表示。为了解决多相机系统的问题，引入了神经翘曲以增强不同相机之间的物体一致性。在广泛使用的自动驾驶数据集上的实验结果表明，HO-Gaussian 在多相机城市数据集上实现了实时照片级渲染。