Zhao Jiashi, Xu Zihan, He Fei, Liu Jianhua, Jiang Zhengang
School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, China.
Department of Radiology, The Second Hospital of Jilin University, Jilin, China.
Int J Comput Assist Radiol Surg. 2025 May 2. doi: 10.1007/s11548-025-03387-0.
Accurate registration of partial-to-partial point clouds is crucial in computer-assisted orthopedic surgery but faces challenges due to incomplete data, noise, and partial overlap. This paper proposes a novel geometric fast registration (GFR) model that addresses these issues through three core modules: point extractor registration (PER), dual attention transformer (DAT), and geometric feature matching (GFM).
PER operates within the frequency domain to enhance point cloud data by attenuating noise and reconstructing incomplete regions. DAT augments feature representation by correlating independent features from source and target point clouds, improving model expressiveness. GFM identifies geometrically consistent point pairs, completing missing data and refining registration accuracy.
We conducted experiments using the clinical bone dataset of 1432 distinct human skeletal samples, comprising ribs, scapulae, and fibula. The proposed model exhibited remarkable robustness and versatility, demonstrating consistent performance across diverse bone structures. When evaluated to noisy, partial-to-partial point clouds with incomplete bone data, the model achieved a mean squared error of 3.57 for rotation and a mean absolute error of 1.29. The mean squared error for translation was 0.002, with a mean absolute error of 0.038.
Our proposed GFR model exhibits exceptional speed and universality, effectively handling point clouds with defects, noise, and partial overlap. Extensive experiments conducted on bone datasets demonstrate the superior performance of our model compared to state-of-the-art methods. The code is publicly available at https://github.com/xzh128/PER .
在计算机辅助骨科手术中，部分到部分点云的精确配准至关重要，但由于数据不完整、噪声和部分重叠等问题面临挑战。本文提出了一种新颖的几何快速配准（GFR）模型，该模型通过三个核心模块来解决这些问题：点提取器配准（PER）、双注意力变换器（DAT）和几何特征匹配（GFM）。
PER在频域内运行，通过衰减噪声和重建不完整区域来增强点云数据。DAT通过关联源点云和目标点云的独立特征来增强特征表示，提高模型的表现力。GFM识别几何上一致的点对，完成缺失数据并提高配准精度。
我们使用了包含肋骨、肩胛骨和腓骨的1432个不同人体骨骼样本的临床骨数据集进行实验。所提出的模型表现出显著的鲁棒性和通用性，在各种骨骼结构上都表现出一致的性能。当对具有不完整骨骼数据的噪声部分到部分点云进行评估时，该模型的旋转均方误差为3.57，平均绝对误差为1.29。平移的均方误差为0.002，平均绝对误差为0.038。
我们提出的GFR模型具有卓越的速度和通用性，能够有效地处理存在缺陷、噪声和部分重叠的点云。在骨数据集上进行的大量实验表明，我们的模型与现有最先进方法相比具有卓越的性能。代码可在https://github.com/xzh128/PER上公开获取。
