夜间自动驾驶场景重建与基于物理的高斯点云
Nighttime Autonomous Driving Scene Reconstruction with Physically-Based Gaussian Splatting
AI总结：
本文提出基于物理的高斯点云方法，提升自动驾驶夜间场景重建质量，实现实时渲染并优于现有方法。
摘要：
本文聚焦于自动驾驶模拟中的夜间场景重建问题。基于神经辐射场（NeRF）和3D高斯点云（3DGS）的方法在自动驾驶场景重建中实现了逼真建模，但主要针对正常光照条件。低光照驾驶场景由于复杂的光照和外观条件，更难建模，导致现有方法性能下降。为了解决这一问题，本文提出了一种将基于物理的渲染整合到3DGS中的新方法，以提升自动驾驶的夜间场景重建。具体而言，我们的方法将基于物理的渲染整合到复合场景的高斯表示中，并联合优化基于双向反射分布函数（BRDF）的材料属性。我们通过全局光照模块显式建模漫反射成分，并通过各向异性球形高斯分布建模镜面成分。结果表明，我们的方法在户外夜间驾驶场景中提升了重建质量，同时保持了实时渲染。在两个真实的自动驾驶数据集上，包括nuScenes和Waymo，经过广泛实验，我们的方法在定量和定性上均优于现有最先进方法。
英文摘要：
This paper focuses on scene reconstruction under nighttime conditions in autonomous driving simulation. Recent methods based on Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) have achieved photorealistic modeling in autonomous driving scene reconstruction, but they primarily focus on normal-light conditions. Low-light driving scenes are more challenging to model due to their complex lighting and appearance conditions, which often causes performance degradation of existing methods. To address this problem, this work presents a novel approach that integrates physically based rendering into 3DGS to enhance nighttime scene reconstruction for autonomous driving. Specifically, our approach integrates physically based rendering into composite scene Gaussian representations and jointly optimizes Bidirectional Reflectance Distribution Function (BRDF) based material properties. We explicitly model diffuse components through a global illumination module and specular components by anisotropic spherical Gaussians. As a result, our approach improves reconstruction quality for outdoor nighttime driving scenes, while maintaining real-time rendering. Extensive experiments across diverse nighttime scenarios on two real-world autonomous driving datasets, including nuScenes and Waymo, demonstrate that our approach outperforms the state-of-the-art methods both quantitatively and qualitatively.
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。
