Aoralscan3 tooth segmentation dataset

The Aoralscan3 dataset includes 1573, 244, and 244 videos for the corresponding sets. The uniform size of the images in the dataset is 640 × 480 pixels.  LabelMe software is employed to accurately mark the boundary and classify the region of each tooth in the datasets.  This dataset is usef for orthodontic treatment. which is one of the research direction of artificial intelligence using current images and previous 3D models to estimate the relative position of individual teeth before and after orthodontic treatment. This dataset can also be used for point cloud-based instance segmentation and for varifying the effectiveness and efficiency of the proposed methods.