CLAIM: Camera-LiDAR Alignment with Intensity and Monodepth

2025-12-15

AI Summary

This work addresses the limitations of manual feature matching and poor robustness in camera–LiDAR extrinsic calibration. We propose an end-to-end, feature-free coarse-to-fine alignment method. Our approach innovatively fuses LiDAR intensity images with monocular depth predictions to establish a dual-loss alignment framework: a structural loss based on patch-wise Pearson correlation ensures geometric consistency, while a mutual information-based texture loss enhances radiometric consistency. To incorporate strong geometric priors, we leverage a pre-trained monocular depth model and design a lightweight spatial search optimization framework. The method exhibits scene adaptability and cross-dataset generalizability. Extensive experiments on KITTI, Waymo, and MIAS-LCEC demonstrate significant improvements over state-of-the-art methods in both calibration accuracy and robustness. Code is publicly available.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

In this paper, we unleash the potential of the powerful monodepth model in camera-LiDAR calibration and propose CLAIM, a novel method of aligning data from the camera and LiDAR. Given the initial guess and pairs of images and LiDAR point clouds, CLAIM utilizes a coarse-to-fine searching method to find the optimal transformation minimizing a patched Pearson correlation-based structure loss and a mutual information-based texture loss. These two losses serve as good metrics for camera-LiDAR alignment results and require no complicated steps of data processing, feature extraction, or feature matching like most methods, rendering our method simple and adaptive to most scenes. We validate CLAIM on public KITTI, Waymo, and MIAS-LCEC datasets, and the experimental results demonstrate its superior performance compared with the state-of-the-art methods. The code is available at https://github.com/Tompson11/claim.

Problem

• Aligns camera and LiDAR data using monodepth and intensity
• Minimizes structure and texture losses without complex feature extraction
• Validates superior performance on public datasets like KITTI and Waymo

Innovation

• Monodepth model for camera-LiDAR calibration
• Coarse-to-fine search minimizing correlation and information losses
• No complex data processing or feature matching required