Cylindrical shape decomposition for 3D segmentation of tubular objects
share
We develop a cylindrical shape decomposition (CSD) algorithm to decompose an object, which is a union of several tubular structures, into its semantic components. We decompose the object using its curve skeleton and translational sweeps. For that, CSD partitions the curve skeleton into maximal-length sub-skeletons over an orientation function, each sub-skeleton corresponds to a semantic component. To find the intersection of the tubular components, CSD translationally sweeps the object in decomposition intervals to identify critical points at which the shape of the object changes substantially. CSD cuts the object at critical points and assigns the same label to parts along the same sub-skeleton, thereby constructing a semantic component. CSD further reconstructs the semantic components between parts using generalized cylinders. We apply CSD for the segmentation of axons in large 3D electron microscopy images, and the decomposition of vascular networks, as well as synthetic objects. We show that CSD outperforms state-of-the-art decomposition techniques in these applications.
READ FULL TEXT
