Dynamic LiDAR Re-simulation using Compositional Neural Fields

no code implementations • 8 Dec 2023 • Hanfeng Wu, Xingxing Zuo, Stefan Leutenegger, Or Litany, Konrad Schindler, Shengyu Huang

We introduce DyNFL, a novel neural field-based approach for high-fidelity re-simulation of LiDAR scans in dynamic driving scenes.