Existing Gaussian splatting methods often fall short in achieving satisfactory novel view synthesis in driving scenes, primarily due to the absence of crafty design and geometric constraints for the involved elements. This paper introduces a novel neural rendering method termed Decoupled Hybrid Gaussian Splatting (DHGS), targeting at promoting the rendering quality of novel view synthesis for static driving scenes. The novelty of this work lies in the decoupled and hybrid pixel-level blender for road and non-road layers, without the conventional unified differentiable rendering logic for the entire scene, while still maintaining consistent and continuous superimposition through the proposed depth-ordered hybrid rendering strategy. Additionally, an implicit road representation comprised of a Signed Distance Field (SDF) is trained to supervise the road surface with subtle geometric attributes. Accompanied by the use of auxiliary transmittance loss and consistency loss, novel images with imperceptible boundary and elevated fidelity are ultimately obtained. Substantial experiments on the Waymo dataset prove that DHGS outperforms the state-of-the-art methods. The project page where more video evidences are given is: https://ironbrotherstyle.github.io/dhgs_web.

翻译：现有高斯溅射方法在驾驶场景中往往难以实现令人满意的新视角合成，主要由于缺乏对场景元素的精巧设计与几何约束。本文提出一种新颖的神经渲染方法——解耦混合高斯溅射（DHGS），旨在提升静态驾驶场景新视角合成的渲染质量。本工作的创新之处在于：针对道路层与非道路层设计了像素级解耦混合融合器，摒弃了传统对整个场景采用统一可微渲染逻辑的做法，同时通过提出的深度排序混合渲染策略保持叠加结果的一致性与连续性。此外，本文训练了由符号距离场（SDF）构成的隐式道路表征，以监督具有精细几何属性的道路表面。配合辅助透射率损失与一致性损失的使用，最终获得了边界无感知且保真度提升的新视角图像。在Waymo数据集上的大量实验证明，DHGS性能优于现有最先进方法。更多视频证据可见项目页面：https://ironbrotherstyle.github.io/dhgs_web。