Segmentation is a fundamental problem in 3D shape analysis and machine learning. The ability to partition a 3D shape into meaningful or functional parts is a vital ingredient of many down stream applications like shape matching, classification and retrieval. Early segmentation methods were based on approaches like fitting primitive shapes to parts or extracting segmentations from feature points. However, such methods had limited success on shapes with more complex geometry. Observing this, research began using geometric features to aid the segmentation, as certain features (e.g. Shape Diameter Function (SDF)) are less sensitive to complex geometry. This trend was also incorporated in the shift to set-wide segmentations, called cosegmentation, which provides a consistent segmentation throughout a shape dataset, meaning similar parts have the same segment identifier. The idea of co-segmentation is that a set of same class shapes (i.e. chairs) contain more information about the class than a single shape would, which could lead to an overall improvement to the segmentation of the individual shapes. Over shown, our method can provide much more accurate segment boundaries. . . . . .
8.19Comparison between provided ShapeNet labels from SAF [8], when displayed on point clouds or projected onto the original mesh. While there are cases where point cloud resolution impacts the projection (black boxes), there are also many incorrectly labelled sections (red boxes