UniCal: a Single-Branch Transformer-Based Model for Camera-to-LiDAR Calibration and Validation

TL;DR

UniCal is a lightweight Transformer-based model that performs camera-to-LiDAR calibration and validation by early fusion of sensor data, achieving state-of-the-art accuracy and enabling transfer learning for validation tasks.

Contribution

The paper introduces UniCal, a novel single-branch Transformer architecture that performs early fusion for C2L calibration, improving efficiency and accuracy over previous methods.

Findings

Achieves state-of-the-art calibration accuracy.

Lightweight architecture suitable for resource-constrained applications.

Transfer learning enables validation without re-training.

Abstract

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.