Many CT slice images are stored with large slice intervals to reduce storage\nsize in clinical practice. This leads to low resolution perpendicular to the\nslice images (i.e., z-axis), which is insufficient for 3D visualization or\nimage analysis. In this paper, we present a novel architecture based on\nconditional Generative Adversarial Networks (cGANs) with the goal of generating\nhigh resolution images of main body parts including head, chest, abdomen and\nlegs. However, GANs are known to have a difficulty with generating a diversity\nof patterns due to a phenomena known as mode collapse. To overcome the lack of\ngenerated pattern variety, we propose to condition the discriminator on the\ndifferent body parts. Furthermore, our generator networks are extended to be\nthree dimensional fully convolutional neural networks, allowing for the\ngeneration of high resolution images from arbitrary fields of view. In our\nverification tests, we show that the proposed method obtains the best scores by\nPSNR/SSIM metrics and Visual Turing Test, allowing for accurate reproduction of\nthe principle anatomy in high resolution. We expect that the proposed method\ncontribute to effective utilization of the existing vast amounts of thick CT\nimages stored in hospitals.\n