Purpose For computer-aided planning of facial bony surgery, the creation of high-resolution 3D-models of the bones by segmenting volume imaging data is a labor-intensive step, especially as metal dental inlays or implants cause severe artifacts that reduce the quality of the computer-tomographic imaging data. This study provides a method to segment accurate, artifact-free 3D surface models of mandibles from CT data using convolutional neural networks. Methods The presented approach cascades two independently trained 3D-U-Nets to perform accurate segmentations of the mandible bone from full resolution CT images. The networks are trained in different settings using three different loss functions and a data augmentation pipeline. Training and evaluation datasets consist of manually segmented CT images from 307 dentate and edentulous individuals, partly with heavy imaging artifacts. The accuracy of the models is measured using overlap-based, surface-based and anatomical-curvature-based metrics. Results Our approach produces high-resolution segmentations of the mandibles, coping with severe imaging artifacts in the CT imaging data. The use of the two-stepped approach yields highly significant improvements to the prediction accuracies. The best models achieve a Dice coefficient of 94.824% and an average surface distance of 0.31 mm on our test dataset. Conclusion The use of two cascaded U-Net allows high-resolution predictions for small regions of interest in the imaging data. The proposed method is fast and allows a user-independent image segmentation, producing objective and repeatable results that can be used in automated surgical planning procedures.