Technologies for merging three-dimensional models of dental impressions

1. A computing device for dental impression scan merging, the computing device comprising:

a processor configured to:

generate a first model and a second model, the first model comprising a first three-dimensional model including a first plurality of geometric faces indicative of a first dental impression of a dental arch of a user, the second model comprising a second three-dimensional model including a second plurality of geometric faces indicative of a second dental impression of the same dental arch of the user, the first model and the second model having a common anatomical feature;

generate a first point cloud of the first model and a second point cloud of the second model;

align the first point cloud and the second point cloud using the common anatomical feature of the first model and the second model, wherein aligning the first point cloud and the second point cloud comprises:

down-sampling points from the first point cloud and from the second point cloud in a gingiva portion of the first model and the second model that is located at least a threshold distance from a gingival-tooth interface; and

aligning the down-sampled first point cloud and the down-sampled second point cloud; and

merge the first model and the second model to generate a merged model, wherein merging the first model and the second model is based on the alignment of the first point cloud and the second point cloud.

2. The computing device of claim 1 , wherein the processor is further configured to transmit information associated with the merged model or to use the information associated with the merged model to manufacture a dental aligner specific to the dental arch of the user and being configured to reposition one or more teeth of the user.

3. The computing device of claim 1 , wherein generating the first point cloud and the second point cloud comprises, for each of the first model and the second model:

identifying vertices of the plurality of geometric faces;

generating, the vertices of the plurality of geometric faces, points for a point cloud; and

computing, for the generated points of the point cloud, a point normal.

4. The computing device of claim 3 , wherein aligning the first point cloud and the second point cloud comprises:

computing, using the first point cloud and the second point cloud, a translation matrix; and

shifting the first point cloud with respect to the second point cloud based on the computed translation matrix to align the first point cloud and the second point cloud.

5. The computing device of claim 3 , wherein the computed normals are surface normals that extend orthogonally from the surface of the model.

6. The computing device of claim 3 , wherein each point corresponds to a vertex of one of the plurality of geometric faces, and wherein the computed normals are vertex normals which extend from the vertices, the vertex normals being computed using a cross product of two edges which form a corresponding vertex.

7. The computing device of claim 1 , wherein the processor is configured to compute a Root Mean Square (RMS) value between a first point of the first point cloud and a second point of the second point cloud, wherein the first point corresponds with the second point.

8. The computing device of claim 7 , wherein the processor is configured to iteratively compute a plurality of translation matrices for shifting one of the first point cloud or the second point cloud to align the first point cloud and the second point cloud based on the computed translation matrices until the RMS value satisfies a threshold.

9. The computing device of claim 1 , wherein the processor is configured to iteratively compute a plurality of translation matrices for shifting one of the first point cloud or the second point cloud to align the first point cloud and the second point cloud based on the computed translation matrices a predetermined number of iterations.

10. A method comprising:

generating, by a computing device, a first model and a second model, the first model comprising a first three-dimensional model including a first plurality of geometric faces indicative of a first dental impression of a dental arch of a user, the second model comprising a second three-dimensional model including a second plurality of geometric faces indicative of a second dental impression of the same dental arch of the user, the first model and the second model having the common anatomical feature;

generating, by the computing device, a first point cloud of the first model and a second point cloud of the second model;

aligning, by the computing device, the first point cloud and the second point cloud using the common anatomical feature of the first model and the second model, wherein aligning the first point cloud and the second point cloud comprises:

down-sampling points from the first point cloud and from the second point cloud in a gingiva portion of the first model and the second model that is located at least a threshold distance from a gingival-tooth interface; and

aligning the down-sampled first point cloud and the down-sampled second point cloud; and

merging, by the computing device, the first model and the second model to generate a merged model, wherein merging the first model and the second model is based on the alignment of the first point cloud and the second point cloud;

wherein generating the first point cloud and the second point cloud comprises, for each of the first model and the second model:

identifying, by the computing device, vertices of the plurality of geometric faces;

generating, by the computing device using the vertices of the plurality of geometric faces, points for a point cloud; and

computing, by the computing device for the generated points of the point cloud, a point normal.

11. The method of claim 10 , wherein aligning the first point cloud and the second point cloud comprises:

computing, by the computing device using the first point cloud and the second point cloud, a translation matrix; and

shifting, by the computing device, the first point cloud with respect to the second point cloud based on the computed translation matrix to align the first point cloud and the second point cloud.

12. The method of claim 10 , wherein the computed normals are surface normals that extend orthogonally from the surface of the model.

13. The method of claim 10 , wherein each point of the point clouds correspond to a vertex of one of the plurality of geometric faces, and wherein the computed normal are vertex normals extending from a vertex of one of the plurality of geometric faces, the vertex normals being computed using a cross product of two edges which form a corresponding vertex.

14. The method of claim 10 , further comprising computing, by the computing device, a Root Mean Square (RMS) value between a first point of the first point cloud and a second point of the second point cloud, wherein the first point corresponds with the second point.

15. The method of claim 14 , wherein the steps of computing the translation matrix and shifting one of the first point cloud or the second point cloud are iteratively performed until the RMS value satisfies a threshold.

16. The method of claim 10 , further comprising manufacturing, based on the merged model, a dental aligner specific to the dental arch of the user and being configured to reposition one or more teeth of the user.

17. A computing device for dental impression scan merging, the computing device comprising:

a processing circuit including a processor and memory, the memory storing instructions that are configured to be executed by the processor to cause the processor to:

generate a first model and a second model, the first model comprising a first three-dimensional model including a first plurality of geometric faces indicative of a first dental impression of a dental arch of a user, the second model comprising a second three-dimensional model including a second plurality of geometric faces indicative of a second dental impression of the same dental arch of the user, the first model and the second model having the common anatomical feature;

generate a first point cloud for the first model and a second point cloud for the second model, wherein generating the first point cloud and the second point cloud comprises, for each of the first model and the second model:

identifying vertices of the plurality of geometric faces;

generating, using the vertices of the plurality of geometric faces, points that together define a point cloud for the respective model;

compute, using the first point cloud and the second point cloud, a translation matrix;

shift the first point cloud with respect to the second point cloud based on the translation matrix to align the first point cloud and the second point cloud using the common anatomical feature of the first model and the second model, wherein shifting the first point cloud with respect to the second point cloud comprises:

down-sampling points from the first point cloud and from the second point cloud in a gingiva portion of the first model and the second model that is located at least a threshold distance from a gingival-tooth interface; and

shifting the down-sampled first point cloud and the down-sampled second point cloud based on the translation matrix; and

generate a merged model that includes data from the first model and the second model based on the alignment of the first point cloud and the second point cloud.

18. The computing device of claim 17 , wherein the memory further stores instructions that are configured to be executed by the processor to cause the processor to manufacture a dental aligner based on the merged model, the dental aligner being specific to the dental arch of the user and being configured to reposition one or more teeth of the user.

19. The computing device of claim 17 , wherein the memory further stores instructions that are configured to be executed by the processor to cause the processor to compute a Root Mean Square (RMS) value between two corresponding points of the first point cloud and the second point cloud; and

wherein the instructions cause the processor to iteratively compute translation matrices and shift one of the first point cloud or the second point cloud based on the computed translation matrices until the RMS value satisfies a threshold.

20. The computing device of claim 17 , wherein the instructions cause the processor to iteratively compute translation matrices and shift one of the first point cloud or the second point cloud based on the computed translation matrices a predetermined number of iterations.