Kolomazník,J., Horácek,J., Krajícek,V., Pelikán,J.
We present in this paper a novel scheme for a very fast implementation of volumetric segmentation using graph cuts. The main benefit of this work is our approach to non-grid region adjacency processing on CUDA which has not been efficiently done yet to our knowledge. Watershed transform radically reduces the number of vertices for graph processing. Everything starting from watershed transformation and ending with graph cut was parallelized and is is done directly on the GPU.