DriveR${}^3$: Feed-Forward Gaussian Reconstruction for Camera-LiDAR Simulation in Autonomous Driving

Cameras and LiDAR provide complementary appearance and geometric information for autonomous driving, making their joint simulation essential for realistic evaluation of multi-sensor perception systems. However, existing joint reconstruction methods typically rely on time-consuming per-scene optimization, while efficient feed-forward reconstruction approaches primarily target visual geometry recovery and image synthesis, leaving joint camera-LiDAR simulation underexplored. To address this gap, we introduce DriveR${}^3$, a feed-forward framework that directly reconstructs a unified dynamic Gaussian scene representation from sparse camera and LiDAR observations. Our key design establishes spatiotemporal LiDAR-Gaussian associations, enabling shared dynamic Gaussian geometry to be jointly learned from complementary image reconstruction and LiDAR range supervision. DriveR${}^3$ further predicts Gaussian-level LiDAR intensity by adaptively fusing multi-source intensity cues. Experiments on nuScenes demonstrate that DriveR${}^3$ enables feed-forward joint camera-LiDAR reconstruction while also improving visual reconstruction quality, highlighting the benefit of complementary sensor information. Compared with the per-scene optimization method SplatAD, DriveR${}^3$ achieves better results on multiple LiDAR reconstruction metrics and an approximately 10x speedup in scene reconstruction.