Dental object classification and 3D model modification

A non-transitory computer readable medium comprising instructions that, when executed by a processing device, cause the processing device to perform operations comprising:

• receiving a plurality of intraoral scans of a dental site;
• processing the plurality of intraoral scans using one or more trained machine learning models to classify points of the plurality of intraoral scans into a plurality of dental classes, wherein the points are classified into first points having a first dental class of the plurality of dental classes and second points having a second dental class of the plurality of dental classes;
• outputting a user interface comprising one or more selectable controls corresponding to the plurality of dental classes and configured to enable a user to select, via the one or more selectable controls, one or more dental classes from among the plurality of dental classes identified in the intraoral scans by the one or more trained machine learning models;
• receiving a user input to exclude the first dental class and to include the second dental class;
• generating a virtual three-dimensional (3D) model of at least a portion of the dental site based on stitching together the plurality of intraoral scans, wherein the virtual 3D model is generated based on stitching together the plurality of intraoral scans using the second points of the plurality of intraoral scans having the second dental class and without using the first points of the plurality of intraoral scans having the first dental class, and wherein the virtual 3D model is generated to include only the second dental class and to exclude the first dental class;
• and
• outputting a view of the virtual 3D model in the user interface, wherein the first points having the first dental class are not included in the view of the virtual 3D model.

A method comprising:

• receiving a plurality of intraoral scans of a dental site;
• processing the plurality of intraoral scans using one or more trained machine learning models to classify points of the plurality of intraoral scans into a plurality of dental classes, wherein the points are classified into first points having a first dental class of the plurality of dental classes and second points having a second dental class of the plurality of dental classes;
• outputting a user interface comprising one or more selectable controls corresponding to the plurality of dental classes and configured to enable a user to select, via the one or more selectable controls, one or more dental classes from among the plurality of dental classes identified in the intraoral scans by the one or more trained machine learning models;
• receiving a user input to exclude the first dental class and to include the second dental class;
• generating a virtual three-dimensional (3D) model of at least a portion of the dental site based on stitching together the plurality of intraoral scans, wherein the virtual 3D model is generated based on stitching together the plurality of intraoral scans using the second points of the plurality of intraoral scans having the second dental class and without using the first points of the plurality of intraoral scans having the first dental class, and wherein the virtual 3D model is generated to include only the second dental class and to exclude the first dental class;
• and
• outputting a view of the virtual 3D model in the user interface, wherein the first points having the first dental class are not included in the view of the virtual 3D model.