UniCal: a Single-Branch Transformer-Based Model for Camera-to-LiDAR Calibration and Validation
This addresses calibration for autonomous driving systems, offering a lightweight solution, but it appears incremental as it builds on existing Transformer and fusion methods.
The paper tackles the problem of Camera-to-LiDAR extrinsic calibration by introducing UniCal, a Transformer-based model that uses early fusion and a single-branch architecture to infer the 6-DoF transformation, achieving state-of-the-art results.
We introduce a novel architecture, UniCal, for Camera-to-LiDAR (C2L) extrinsic calibration which leverages self-attention mechanisms through a Transformer-based backbone network to infer the 6-degree of freedom (DoF) relative transformation between the sensors. Unlike previous methods, UniCal performs an early fusion of the input camera and LiDAR data by aggregating camera image channels and LiDAR mappings into a multi-channel unified representation before extracting their features jointly with a single-branch architecture. This single-branch architecture makes UniCal lightweight, which is desirable in applications with restrained resources such as autonomous driving. Through experiments, we show that UniCal achieves state-of-the-art results compared to existing methods. We also show that through transfer learning, weights learned on the calibration task can be applied to a calibration validation task without re-training the backbone.