We present DrivingGaussian an efficient and effective framework for surrounding dynamic
autonomous driving scenes. For complex scenes with moving objects we first sequentially …

This paper targets high-fidelity and real-time view synthesis of dynamic 3D scenes at 4K
resolution. Recent methods on dynamic view synthesis have shown impressive rendering …

Holistic understanding of urban scenes based on RGB images is a challenging yet important
problem. It encompasses understanding both the geometry and appearance to enable novel …

The rapid growth of 3D Gaussian Splatting (3DGS) has revolutionized neural rendering,
enabling real-time production of high-quality renderings. However, the previous 3DGS …

We estimate the radiance field of large-scale dynamic areas from multiple vehicle captures
under varying environmental conditions. Previous works in this domain are either restricted …

Closed-loop simulation is essential for advancing end-to-end autonomous driving systems.
Contemporary sensor simulation methods, such as NeRF and 3DGS, rely predominantly on …

Advancements in neural signed distance fields (SDFs) have enabled modeling 3D surface
geometry from a set of 2D images of real-world scenes. Baking neural SDFs can extract …

Neural implicit fields have been a de facto standard in novel view synthesis. Recently there
exist some methods exploring fusing multiple modalities within a single field aiming to share …

Online dense mapping of urban scenes is of paramount importance for scene understanding
of autonomous navigation. Traditional online dense mapping methods fuse sensor …

Autonomous driving simulation system plays a crucial role in enhancing self-driving data
and simulating complex and rare traffic scenarios, ensuring navigation safety. However …