Selective dental arch model generation

A system comprising:

• an intraoral scanner configured to generate a plurality of two-dimensional images of a dental site, each two-dimensional image comprising data representing a surface of the dental site;
• and
• a computing device communicatively coupled to the intraoral scanner, the computing device comprising at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the computing device to:
• receive the plurality of two-dimensional images from the intraoral scanner;
• process data from each two-dimensional image of the plurality of two-dimensional images using a trained machine learning model that has been trained to classify regions of dental sites, wherein, for each two-dimensional image, the trained machine learning model outputs classification data identifying at least a tooth region and a gum region in the two-dimensional image;
• and
• selectively generate a three-dimensional model of the dental site from the plurality of two-dimensional images based on the classification data, wherein the three-dimensional model excludes at least a portion of data corresponding to regions that are classified as neither the tooth region nor the gum region.