DHGS: Decoupled Hybrid Gaussian Splatting for Driving Scene
This work addresses the problem of low-quality novel view synthesis in driving scenes for applications like autonomous driving, though it is incremental as it builds on existing Gaussian splatting methods.
The paper tackles novel view synthesis in static driving scenes by introducing Decoupled Hybrid Gaussian Splatting (DHGS), which uses a decoupled pixel-level blender for road and non-road layers and an implicit road representation with SDF supervision, resulting in improved rendering quality as demonstrated on the Waymo dataset.
Existing Gaussian splatting methods often fall short in achieving satisfactory novel view synthesis in driving scenes, primarily due to the absence of crafty designs 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. Still, consistency and continuity in superimposition are preserved through the proposed depth-ordered hybrid rendering strategy. Additionally, an implicit road representation comprised of a Signed Distance Function (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.