We introduce a statistical extension of the classic Poisson Surface Reconstruction algorithm for recovering shapes from 3D point clouds. Instead of outputting an implicit function, we represent the reconstructed shape as a modified Gaussian Process, which allows us to conduct statistical queries (e.g., the likelihood of a point in space being on the surface or inside a solid). We show that this perspective: improves PSR's integration into the online scanning process, broadens its application realm, and opens the door to other lines of research such as applying task-specific priors.
翻译:我们引入经典的 Poisson 地表重建算法的统计延伸, 用于从 3D 点云中恢复形状。 我们不是输出一个隐含功能,而是将重建的形状作为修改的高西亚进程, 从而使我们能够进行统计查询( 例如, 空间点在表面或固体中的可能性 ) 。 我们展示了这个观点: 改进 PSR 融入在线扫描过程, 扩大其应用范围, 并为其他研究线打开大门, 比如应用特定任务前科 。