Abstract: Machine learning, or geometric deep learning, applied to various dental processes and 5 solutions. In particular, generative adversarial networks apply machine learning to smile design—finished smile, appliance rendering, scan cleanup, restoration appliance design, crown and bridges design, and virtual debonding. Vertex and edge classification apply machine learning to gum versus teeth detection, teeth type segmentation, and brackets and other orthodontic hardware. Regression applies machine learning to coordinate systems, diagnostics, case complexity, and 0 prediction of treatment duration. Automatic encoders and clustering apply machine learning to grouping of doctors, or technicians, and preferences.

Abstract: An automated method for generating a final setup for orthodontic treatment. The method includes receiving a digital 3D model of teeth in an initial state. The method computes a scoring function based upon metrics related to the initial state to generate a corresponding score, perturbs the state of the teeth through translations and rotations of a tooth or set of teeth to generate a perturbed state of the teeth, and updates the state of the teeth based upon the score and the perturbed state of the teeth to generate one or more final setups representing a final state of the teeth after the orthodontic treatment.

Abstract: A method for determining virtual articulation from dental scans. The method includes receiving digital 3D models of a person's maxillary and mandibular arches, and digital 3D models of a plurality of different bite poses of the arches. The digital 3D models of the maxillary and mandibular arches are registered with the bite poses to generate transforms defining spatial relationships between the arches for the bite poses. Based upon the digital 3D models and transforms, the method computes a pure rotation axis representation for each bite pose of the mandibular arch with respect to the maxillary arch. The virtual articulation can be used in making restorations or for diagnostic purposes.

Abstract: A method for determining virtual articulation from dental scans. The method includes receiving digital 3D models of a person's maxillary and mandibular arches, and digital 3D models of a plurality of different bite poses of the arches. The digital 3D models of the maxillary and mandibular arches are registered with the bite poses to generate transforms defining spatial relationships between the arches for the bite poses. Based upon the digital 3D models and transforms, the method computes a pure rotation axis representation for each bite pose of the mandibular arch with respect to the maxillary arch. The virtual articulation can be used in making restorations or for diagnostic purposes.

Abstract: A method for determining virtual articulation from dental scans. The method includes receiving digital 3D models of a person's maxillary and mandibular arches, and digital 3D models of a plurality of different bite poses of the arches. The digital 3D models of the maxillary and mandibular arches are registered with the bite poses to generate transforms defining spatial relationships between the arches for the bite poses. Based upon the digital 3D models and transforms, the method computes a pure rotation axis representation for each bite pose of the mandibular arch with respect to the maxillary arch. The virtual articulation can be used in making restorations or for diagnostic purposes.

Abstract: A method for determining virtual articulation from dental scans. The method includes receiving digital 3D models of a person's maxillary and mandibular arches, and digital 3D models of a plurality of different bite poses of the arches. The digital 3D models of the maxillary and mandibular arches are registered with the bite poses to generate transforms defining spatial relationships between the arches for the bite poses. Based upon the digital 3D models and transforms, the method computes a pure rotation axis representation for each bite pose of the mandibular arch with respect to the maxillary arch. The virtual articulation can be used in making restorations or for diagnostic purposes.