Although neural radiance fields (NeRFs) have achieved triumphs in image novel view synthesis (NVS), LiDAR NVS remains largely unexplored. Previous LiDAR NVS methods employ a simple shift from image NVS methods while ignoring the dynamic nature and the large-scale reconstruction problem of LiDAR point clouds. In light of this, we propose LiDAR4D, a differentiable LiDAR-only framework for novel space-time LiDAR view synthesis. In consideration of the sparsity and large-scale characteristics, we design a 4D hybrid representation combined with multi-planar and grid features to achieve effective reconstruction in a coarse-to-fine manner. Furthermore, we introduce geometric constraints derived from point clouds to improve temporal consistency. For the realistic synthesis of LiDAR point clouds, we incorporate the global optimization of ray-drop probability to preserve cross-region patterns. Extensive experiments on KITTI-360 and NuScenes datasets demonstrate the superiority of our method in accomplishing geometry-aware and time-consistent dynamic reconstruction. Codes are available at https://github.com/ispc-lab/LiDAR4D.

翻译：尽管神经辐射场（NeRF）在图像新颖视角合成（NVS）方面取得了成功，但LiDAR新颖视角合成仍鲜有探索。先前的LiDAR NVS方法简单沿用了图像NVS方法，却忽略了LiDAR点云的动态特性与大尺度重建问题。鉴于此，我们提出LiDAR4D——一种可微分的纯LiDAR框架，用于新颖时空LiDAR视角合成。考虑到点云的稀疏性与大尺度特征，我们设计了一种结合多平面与网格特征的4D混合表示，以由粗到精的方式实现高效重建。此外，我们引入源自点云的几何约束以提升时间一致性。为逼真合成LiDAR点云，我们通过全局优化射线丢弃概率来保留跨区域模式。在KITTI-360与NuScenes数据集上的大量实验表明，该方法在实现几何感知且时间一致的动态重建方面具有优越性。代码已开源：https://github.com/ispc-lab/LiDAR4D。