散乱点数据的Bayesian曲面重建

Surface reconstruction from scattered points based on Bayesian

针对带噪声的点云数据提出了一种基于贝叶斯(Bayesian)统计理论的曲面重建算法。算法的主要思想是在可能的重建概率空间上寻找最大后验概率。首先,分别计算测量过程数学模型和曲面先验概率模型;其次,通过共轭梯度优化算法确定每一个点的最大后验重建位置;最后,应用Surface Splatting算法绘制点模型。实验结果表明,该先验概率模型不仅能去除扫描点云数据的噪声,同时还能增强曲面的细节特征。和已有的研究工作相比,本算法能获得更好的重建结果。

A surface reconstruction algorithm from noisy point clouds based on Bayesian statistics was presented. The main idea is to perform a search for a maximum of posterior probability （MAP） in the space of possible constructions. First, a mathematical model of noisy measurement process and a prior over surface shapes were computed respectively. Second, an approximate MAP-reconstruction for each point was found by using a conjugated gradient optimization method. Finally, the Surface Splatting algorithm was applied to render the constructed point-based models. Experiments show that the proposed prior can smooth away noise of the scanned point clouds while enhancing visible surface features. Compared to previous work in this area, the algorithm in this paper can obtain better reconstructing results.