Systems and methods for constructing a three-dimensional model from two-dimensional images

Abstract

A system includes a model generation system configured to receive one or more dental images corresponding to a dental arch of a user, generate a three-dimensional (3D) model of at least a portion of the dental arch of the user by applying the one or more dental images to a machine learning model to generate the 3D model where the machine learning model is trained based on at least one of one or more training images or one or more three-dimensional (3D) training models, and output the 3D model of the at least the portion of the dental arch to one or more computing devices.

What is claimed is: 
     
         1 . A method comprising:
 receiving, by one or more processors, one or more dental images corresponding to a dental arch of a user;   generating, by the one or more processors, a three-dimensional (3D) model of at least a portion of the dental arch of the user by applying the one or more dental images to a machine learning model to generate the 3D model, the machine learning model trained based on at least one of one or more training images or one or more three-dimensional (3D) training models; and   outputting, by the one or more processors, the 3D model of the at least the portion of the dental arch to one or more computing devices.   
     
     
         2 . The method of  claim 1 , wherein the one or more dental images comprise at least one of an image of a dental impression of the dental arch of the user or an image of the dental arch of the user. 
     
     
         3 . The method of  claim 1 , wherein the 3D model is a first 3D model, and wherein the method further comprises generating, by the one or more processors, a second 3D model of the at least the portion of the dental arch of the user based on the first 3D model of the at least the portion of the dental arch of the user. 
     
     
         4 . The method of  claim 3 , further comprising training, by the one or more processors, the machine learning model using the one or more training images and the 3D training models. 
     
     
         5 . The method of  claim 1 , wherein the 3D model of the at least the portion of the dental arch is a first 3D model, the method further comprising merging the first 3D model with a second 3D model. 
     
     
         6 . The method of  claim 5 , wherein the second 3D model is a second 3D model of the at least the portion of the dental arch. 
     
     
         7 . The method of  claim 5 , wherein merging the first 3D model with the second 3D model comprises generating a merged model comprising a portion of the first 3D model and a portion of the second 3D model. 
     
     
         8 . The method of  claim 1 , wherein the one or more dental images are one or more first dental images, wherein the 3D model is a first 3D model, and wherein the method further comprises:
 receiving one or more second dental images corresponding to the dental arch; and   generating a second 3D model of the at least the portion of the dental arch of the user by applying the one or more second dental images to the machine learning model.   
     
     
         9 . The method of  claim 1 , further comprising:
 generating a user interface for rendering at a user device that includes the generated 3D model; and   transmitting, to the user device, the generated user interface for rendering to the user.   
     
     
         10 . The method of  claim 9 , further comprising:
 displaying, by the user interface at the user device, the generated 3D model;   receiving an input from the user device manipulating a model tooth of the generated 3D model to reposition the model tooth; and   transmitting an updated 3D model based on the input to a manufacturing computer system for manufacturing a dental aligner configured to reposition a user's tooth based on the updated 3D model.   
     
     
         11 . The method of  claim 9 , further comprising:
 displaying, by the user interface at the user device, a plurality of stages of a treatment plan based on the 3D model.   
     
     
         12 . The method of  claim 1 , wherein the one or more training images and the one or more 3D training models correspond to respective dental arches. 
     
     
         13 . A system comprising:
 a model generation system configured to:
 receive one or more dental images corresponding to a dental arch of a user; 
 generate a three-dimensional (3D) model of at least a portion of the dental arch of the user by applying the one or more dental images to a machine learning model to generate the 3D model, the machine learning model trained based on at least one of one or more training images or one or more three-dimensional (3D) training models; and 
 output the 3D model of the at least the portion of the dental arch to one or more computing devices. 
   
     
     
         14 . The system of  claim 13 , wherein the one or more dental images comprise at least one of an image of a dental impression of the dental arch of the user or an image of the dental arch of the user. 
     
     
         15 . The system of  claim 13 , wherein the 3D model is a first 3D model, and wherein the model generation system is further configured to generate a second 3D model of the at least the portion of the dental arch of the user based on the first 3D model of the at least the portion of the dental arch of the user. 
     
     
         16 . The system of  claim 13 , wherein the 3D model of the at least the portion of the dental arch is a first 3D model, the model generation system further configured to merge the first 3D model with a second 3D model. 
     
     
         17 . The system of  claim 16 , wherein the model generation system is further configured to generate a merged model comprising a portion of the first 3D model and a portion of the second 3D model. 
     
     
         18 . The system of  claim 13 , wherein the one or more dental images are one or more first dental images, wherein the 3D model is a first 3D model, and wherein the model generation system is further configured to:
 receive one or more second dental images corresponding to the dental arch; and   generate a second 3D model of the at least the portion of the dental arch of the user by applying the one or more second dental images to the machine learning model.   
     
     
         19 . The system of  claim 13 , wherein the model generation system is further configured to:
 generate a user interface for rendering at a user device that includes the generated 3D model; and   transmit, to the user device, the generated user interface for rendering to the user.   
     
     
         20 . A non-transitory computer-readable media comprising computer-readable instructions stored thereon that, when executed by one or more processors, cause the one or more processors to:
 receive one or more dental images corresponding to a dental arch of a user;   generate a three-dimensional (3D) model of at least a portion of the dental arch of the user by applying the one or more dental images to a machine learning model to generate the 3D model, the machine learning model trained based on at least one of one or more training images or one or more three-dimensional (3D) training models; and   output the 3D model of the at least the portion of the dental arch to one or more computing devices.