DST-Calib: A Dual-Path, Self-Supervised, Target-Free LiDAR-Camera Extrinsic Calibration Network

TL;DR

DST-Calib introduces a novel self-supervised, target-free LiDAR-camera calibration method that uses double-sided data augmentation and a dual-path framework to improve robustness, accuracy, and online adaptability in diverse environments.

Contribution

It is the first to propose a self-supervised, target-free calibration network with double-sided augmentation and a difference map for cross-modal feature correlation.

Findings

Outperforms existing methods in generalizability across five benchmark datasets.

Operates in an online, fully adaptive manner without calibration targets.

Reduces model complexity while improving calibration accuracy.

Abstract

LiDAR-camera extrinsic calibration is essential for multi-modal data fusion in robotic perception systems. However, existing approaches typically rely on handcrafted calibration targets (e.g., checkerboards) or specific, static scene types, limiting their adaptability and deployment in real-world autonomous and robotic applications. This article presents the first self-supervised LiDAR-camera extrinsic calibration network that operates in an online fashion and eliminates the need for specific calibration targets. We first identify a significant generalization degradation problem in prior methods, caused by the conventional single-sided data augmentation strategy. To overcome this limitation, we propose a novel double-sided data augmentation technique that generates multi-perspective camera views using estimated depth maps, thereby enhancing robustness and diversity during training. Built upon this augmentation strategy, we design a dual-path, self-supervised calibration framework that reduces the dependence on high-precision ground truth labels and supports fully adaptive online calibration. Furthermore, to improve cross-modal feature association, we replace the traditional dual-branch feature extraction design with a difference map construction process that explicitly correlates LiDAR and camera features. This not only enhances calibration accuracy but also reduces model complexity. Extensive experiments conducted on five public benchmark datasets, as well as our own recorded dataset, demonstrate that the proposed method significantly outperforms existing approaches in terms of generalizability.