LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis
This work addresses the challenge of synthesizing dynamic LiDAR views for applications like autonomous driving, representing an incremental advancement by adapting neural fields to LiDAR-specific issues.
The paper tackles the problem of novel space-time view synthesis for LiDAR point clouds, which remains largely unexplored compared to image-based methods, and achieves superior geometry-aware and time-consistent dynamic reconstruction on KITTI-360 and NuScenes datasets.
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.