Rock-mass point-cloud registration is a critical yet challenging task in the fields of geology and engineering. Currently, the lack of dedicated datasets for rock-mass pointcloud registration significantly limits the development and application of advanced algorithms in this area. To address this gap, we introduce RockCloud-Align, a large-scale dataset specifically designed for rock-mass point-cloud registration. Created using high-resolution LiDAR scans, this dataset covers a wide range of geological scenarios with varying densities and includes over 14,000 meticulously curated point-cloud pairs. RockCloud-Align provides a comprehensive benchmark for evaluating registration algorithms, along with a robust evaluation protocol to standardize the assessment of these methods. Building upon this dataset, we propose a novel registration method that eliminates the dependence on feature points and random sampling consensus, ensuring high efficiency and precision across diverse scenes and densities. Extensive experiments demonstrate that the proposed method significantly outperforms existing approaches in both accuracy and computational efficiency.
Loading....