P2GS: 基于物理先验的高斯点云法用于光度一致的城市重建
P2GS: Physical Prior-guided Gaussian Splatting for Photometrically Consistent Urban Reconstruction
AI总结：
本文提出P2GS，一种基于物理先验的高斯点云法，用于解决自动驾驶中由于异质相机管道和动态户外照明导致的光度不一致问题，通过联合分解视图不变的线性HDR光场、每视图曝光尺度和色调映射函数，提升光度一致性与光照一致性。
摘要：
3D高斯点云法（3DGS）最近作为一种强大的显式表示方法出现，使其能够实现快速、高保真的渲染，成为自动驾驶闭环模拟器和感知模型的有前途的基础。然而，传统3DGS隐式假设不同视图之间具有一致的曝光和色调映射。真实驾驶数据由于异质相机管道和动态户外照明而违反这一假设，将曝光差异和传感器噪声烘焙到光场中，导致在静态背景中产生伪影和不一致的照明，这对现实模拟至关重要。这些问题是自动驾驶中尤为突出的，因为稀疏的视点、变化的曝光和户外照明相互作用，而以往的工作主要针对动态物体重建，忽略了跨视图的光度一致性。为了解决这一限制，我们引入了P2GS，一种物理一致的高斯点云框架，仅从LDR图像中联合分解视图不变的线性HDR光场、每视图曝光尺度和色调映射函数。P2GS采用基于物理图像形成过程的统一优化策略，强制相对曝光一致性和HDR域光流正则化。这产生了一个对跨相机照明差异具有鲁棒性的光场，同时保持标准3DGS的实时效率。在真实和模拟驾驶环境中进行的实验表明，P2GS在LDR重建中匹配或超越了先前的方法，同时在多样化的场景中提供了显著改进的光度一致性、可靠的曝光归一化和物理一致的照明。
英文摘要：
3D Gaussian Splatting (3DGS) has recently emerged as a powerful explicit representation enabling fast, high-fidelity rendering, making it a promising foundation for closed-loop simulators and perception models in autonomous driving. However, conventional 3DGS implicitly assumes consistent exposure and tone mapping across views. Real driving data violates this assumption due to heterogeneous camera pipelines and dynamic outdoor illumination, baking exposure discrepancies and sensor noise into the radiance field and producing artifacts and inconsistent illumination especially in static backgrounds crucial for realistic simulation. These issues are amplified in autonomous driving, where sparse viewpoints, varying exposures, and outdoor lighting interact, while prior work mainly targets dynamic-object reconstruction and overlooks cross-view photometric consistency. To address this limitation, we introduce P2GS, a physically consistent Gaussian Splatting framework that jointly decomposes a view-invariant linear HDR radiance field, per-view exposure scales, and tone-mapping functions from only LDR images without HDR supervision. P2GS employs a unified optimization strategy grounded in the physical image-formation process, enforcing relative-exposure consistency and HDR-domain radiance regularization. This yields a radiance field robust to inter-camera illumination differences while preserving the real-time efficiency of standard 3DGS. Experiments across real and simulated driving environments show that P2GS matches or surpasses prior methods in LDR reconstruction while providing substantially improved photometric consistency, reliable exposure normalization, and physically coherent illumination across diverse scenes.
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。
