3DGS-Calib: 3D Gaussian Splatting for Multimodal SpatioTemporal Calibration
This work addresses the need for faster and reliable calibration in autonomous driving and robotics, though it is incremental as it adapts an existing rendering method to a known bottleneck.
The paper tackles the problem of slow training in targetless multimodal sensor calibration by using 3D Gaussian Splatting instead of implicit neural representations, achieving a substantial speed-up while maintaining accuracy and robustness on the KITTI-360 dataset.
Reliable multimodal sensor fusion algorithms require accurate spatiotemporal calibration. Recently, targetless calibration techniques based on implicit neural representations have proven to provide precise and robust results. Nevertheless, such methods are inherently slow to train given the high computational overhead caused by the large number of sampled points required for volume rendering. With the recent introduction of 3D Gaussian Splatting as a faster alternative to implicit representation methods, we propose to leverage this new rendering approach to achieve faster multi-sensor calibration. We introduce 3DGS-Calib, a new calibration method that relies on the speed and rendering accuracy of 3D Gaussian Splatting to achieve multimodal spatiotemporal calibration that is accurate, robust, and with a substantial speed-up compared to methods relying on implicit neural representations. We demonstrate the superiority of our proposal with experimental results on sequences from KITTI-360, a widely used driving dataset.