Dynamic LiDAR Re-simulation using Compositional Neural Fields

arXiv:2312.05247v2 Announce Type: replace
Abstract: We introduce DyNFL, a novel neural field-based approach for high-fidelity re-simulation of LiDAR scans in dynamic driving scenes. DyNFL processes LiDAR measurements from dynamic environments, accompanied by bounding boxes of moving objects, to construct an editable neural field. This field, comprising separately reconstructed static background and dynamic objects, allows users to modify viewpoints, adjust object positions, and seamlessly add or remove objects in the re-simulated scene. A key innovation of our method is the neural …

abstract arxiv construct cs.cv driving dynamic environments fidelity fields lidar moving novel objects processes scans simulation type