PseudoCal: Towards Initialisation-Free Deep Learning-Based Camera-LiDAR Self-Calibration

TL;DR

PseudoCal introduces a novel deep learning-based method for camera-LiDAR self-calibration that operates without initial estimates, using pseudo-LiDAR to achieve accurate 3D calibration in autonomous systems.

Contribution

It proposes PseudoCal, a new approach that eliminates the need for initial parameter estimates in camera-LiDAR calibration by leveraging pseudo-LiDAR in 3D space.

Findings

Performs one-shot calibration without initial estimates

Handles extreme calibration cases effectively

Works directly in 3D space for improved accuracy

Abstract

Camera-LiDAR extrinsic calibration is a critical task for multi-sensor fusion in autonomous systems, such as self-driving vehicles and mobile robots. Traditional techniques often require manual intervention or specific environments, making them labour-intensive and error-prone. Existing deep learning-based self-calibration methods focus on small realignments and still rely on initial estimates, limiting their practicality. In this paper, we present PseudoCal, a novel self-calibration method that overcomes these limitations by leveraging the pseudo-LiDAR concept and working directly in the 3D space instead of limiting itself to the camera field of view. In typical autonomous vehicle and robotics contexts and conventions, PseudoCal is able to perform one-shot calibration quasi-independently of initial parameter estimates, addressing extreme cases that remain unsolved by existing approaches.