Wang Xiaoqiang, Wang Qing, Sun Yang, Liu Shengyi
School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China.
Sensors (Basel). 2026 Mar 5;26(5):1650. doi: 10.3390/s26051650.
High-fidelity 4D reconstruction of dynamic scenes is pivotal for immersive simulation yet remains challenging due to the photometric inconsistencies inherent in multi-view sensor arrays. Standard 3D Gaussian Splatting (3DGS) strictly adheres to the brightness constancy assumption, failing to distinguish between intrinsic scene radiance and transient brightness shifts caused by independent auto-exposure (AE), auto-white-balance (AWB), and non-linear ISP processing. This misalignment often forces the optimization process to compensate for spectral discrepancies through incorrect geometric deformation, resulting in severe temporal flickering and spatial floating artifacts. To address these limitations, we present Lumina-4DGS, a robust framework that harmonizes spatiotemporal geometry modeling with a hierarchical exposure compensation strategy. Our approach explicitly decouples photometric variations into two levels: a Global Exposure Affine Module that neutralizes sensor-specific AE/AWB fluctuations and a Multi-Scale Bilateral Grid that residually corrects spatially varying non-linearities, such as vignetting, using luminance-based guidance. Crucially, to prevent these powerful appearance modules from masking geometric flaws, we introduce a novel SSIM-Gated Optimization mechanism. This strategy dynamically gates the gradient flow to the exposure modules based on structural similarity. By ensuring that photometric enhancement is only activated when the underlying geometry is structurally reliable, we effectively prioritize geometric accuracy over photometric overfitting. Extensive experiments validate the quantitative superiority of Lumina-4DGS. On the Waymo Open Dataset, our method achieves a state-of-the-art Full Image PSNR of 31.12 dB while minimizing geometric errors to a Depth RMSE of 1.89 m and Chamfer Distance of 0.215 m. Furthermore, on our highly challenging self-collected surround-view dataset featuring severe unconstrained illumination shifts, Lumina-4DGS yields a significant 2.13 dB PSNR improvement over recent driving-scene baselines. These results confirm that our framework achieves photorealistic, exposure-invariant novel view synthesis while maintaining superior geometric consistency across heterogeneous camera inputs.
动态场景的高保真4D重建对于沉浸式模拟至关重要，但由于多视图传感器阵列中固有的光度不一致性，仍然具有挑战性。标准的3D高斯喷溅法（3DGS）严格遵循亮度恒定假设，无法区分固有场景辐射和由独立自动曝光（AE）、自动白平衡（AWB）以及非线性图像信号处理（ISP）引起的瞬时光照变化。这种不匹配常常迫使优化过程通过不正确的几何变形来补偿光谱差异，从而导致严重的时间闪烁和空间浮动伪影。为了解决这些限制，我们提出了Lumina - 4DGS，这是一个强大的框架，它将时空几何建模与分层曝光补偿策略相结合。我们的方法明确地将光度变化解耦为两个层次：一个全局曝光仿射模块，用于抵消特定传感器的AE/AWB波动；一个多尺度双边网格，使用基于亮度的引导对空间变化的非线性（如渐晕）进行残差校正。至关重要的是，为了防止这些强大的外观模块掩盖几何缺陷，我们引入了一种新颖的结构相似性（SSIM）门控优化机制。该策略基于结构相似性动态地控制梯度流向曝光模块。通过确保仅在底层几何结构可靠时才激活光度增强，我们有效地将几何精度置于光度过拟合之上。大量实验验证了Lumina - 4DGS在数量上的优越性。在Waymo开放数据集上，我们的方法实现了31.12 dB的最先进全图像峰值信噪比（PSNR），同时将几何误差最小化至深度均方根误差（RMSE）为1.89米，倒角距离为0.215米。此外，在我们极具挑战性的自采集全景数据集上，该数据集具有严重的无约束光照变化，Lumina - 4DGS比最近的驾驶场景基线在PSNR上显著提高了2.13 dB。这些结果证实，我们的框架实现了逼真的、曝光不变的新视图合成，同时在异构相机输入中保持了卓越的几何一致性。
