Positioning individual three-dimensional model teeth based on two-dimensional images

1. A method comprising:

generating, by one or more processors, a first 3D model of a dentition, the dentition comprising a model tooth in a first position;

receiving, by the one or more processors, a digital representation comprising a patient tooth, the patient tooth corresponding to the model tooth of the first 3D model;

determining, by the one or more processors, a virtual camera parameter associated with the digital representation;

adjusting, by the one or more processors, the virtual camera parameter to determine a 3D position of the corresponding patient tooth;

moving, by the one or more processors, the model tooth of the first 3D model from the first position to a second position, wherein the second position corresponds to the 3D position of the corresponding patient tooth; and

generating, by the one or more processors, a second 3D model comprising the model tooth of the first 3D model in the second position.

2. The method of claim 1 , wherein the virtual camera parameter comprises an extrinsic parameter, the extrinsic parameter defining at least one of a translational matrix or a rotational matrix of a camera used to capture the digital representation.

3. The method of claim 1 , wherein the virtual camera parameter comprises an intrinsic parameter, the intrinsic parameter defining a distortion of a camera used to capture the digital representation.

4. The method of claim 1 , further comprising establishing a reference point of the 3D model, wherein the model tooth of the first 3D model moves relative to the reference point, the reference point comprising a predefined movement.

5. The method of claim 4 , wherein the reference point comprises a first molar or a second molar of the 3D model, wherein the predefined movement of the first molar or the second molar comprises remaining stationary.

6. The method of claim 1 , further comprising:

receiving, by the one or more processors, a plurality of digital representations, wherein the plurality of digital representations comprise at least one of a plurality of individually captured images or a video;

identifying, by the one or more processors, a subset of the plurality of digital representations, wherein each of the subset of the plurality of digital representations comprises a predetermined portion of the corresponding patient tooth; and

associating, by the one or more processors, the subset of the plurality of digital representations with the corresponding patient tooth;

wherein the second position of the model tooth is based on the subset of the plurality of digital representations associated with the corresponding patient tooth and the virtual camera parameter.

7. The method of claim 1 , further comprising:

limiting, by the one or more processors, a tooth movement based on a tooth movement parameter; and

applying, by the one or more processors, a penalty to the tooth movement when the tooth movement deviates from the tooth movement parameter.

8. The method of claim 7 , wherein the tooth movement parameter defines a range of possible tooth movements.

9. The method of claim 7 , further comprising:

accessing, by the one or more processors, a tooth movement library to determine the tooth movement parameter for the model tooth of the first 3D model; and

limiting, by the one or more processors, available tooth movements of the model tooth of the first 3D model based on the tooth movement parameter from the tooth movement library.

10. The method of claim 7 , wherein the penalty prevents the model tooth from undergoing a possible tooth movement based on the penalty reaching a predefined threshold.

11. The method of claim 7 , further comprising:

designating, by the one or more processors, a feature in the digital representation as an obstruction, wherein the tooth movement comprising moving the model tooth behind the obstruction satisfies the tooth movement parameter.

12. The method of claim 1 , further comprising:

receiving, by the one or more processors, a plurality of digital representations, including the digital representation;

estimating, by the one or more processors, the virtual camera parameter based on a first digital representation of the plurality of digital representations; and

adjusting, by the one or more processors, the virtual camera parameter based on one or more of the remaining digital representations of the plurality of digital representations until at least one of:

a size of an adjustment is less than a threshold value; or

a threshold number of the remaining digital representations has been analyzed to adjust the virtual camera parameter.

13. The method of claim 1 , further comprising:

adjusting, iteratively, by the one or more processors, the virtual camera parameter to determine the 3D position of the corresponding patient tooth; and

applying, by the one or more processors, a threshold to an iterative tooth adjustment count, the threshold defining when the model tooth is in the second position within a threshold degree of accuracy.

14. The method of claim 13 , wherein the threshold comprises at least one of a fixed number of iterations or a plateau in a loss function.

15. The method of claim 1 , wherein the one or more processors do not use a treatment plan to generate the second 3D model with the model tooth in the second position, wherein the treatment plan defines an expected position of the corresponding patient tooth.

16. The method of claim 1 , further comprising:

modifying a geometry of the corresponding patient tooth of the digital representation based on the virtual camera parameter; and

comparing the first position of the model tooth of the first 3D model with the position of the corresponding patient tooth of the digital representation based on the modified geometry of the corresponding patient tooth of the digital representation.

17. The method of claim 1 , wherein a shape of the model tooth is based on a shape of a template tooth from a template model dentition.

18. A system comprising:

one or more processors; and

a memory coupled with the one or more processors, wherein the memory is configured to store instructions that, when executed by the one or more processors, cause the one or more processors to:

generate a first 3D model of a dentition, the dentition comprising a model tooth in a first position;

receive a digital representation comprising a patient tooth, the patient tooth corresponding to the model tooth of the first 3D model;

determine a virtual camera parameter associated with the digital representation;

adjust the virtual camera parameter to determine a 3D position of the corresponding patient tooth;

move the model tooth of the first 3D model from the first position to a second position, the second position corresponding to the 3D position of the corresponding patient tooth; and

generate a second 3D model comprising the model tooth of the first 3D model in the second position.

19. The system of claim 18 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:

receive a plurality of digital representations, wherein the plurality of digital representations comprise at least one of a plurality of individually captured images or a video;

identify a subset of the plurality of digital representations, wherein each of the subset of the plurality of digital representations comprises a predetermined portion of the corresponding patient tooth; and

associate the subset of the plurality of digital representations with the corresponding patient tooth;

wherein the second position of the model tooth is based on the subset of the plurality of digital representations associated with the corresponding patient tooth and the virtual camera parameter.

20. A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:

generate a first 3D model of a dentition, the dentition comprising a model tooth in a first position;

receive a digital representation comprising a patient tooth, the patient tooth corresponding to the model tooth of the first 3D model;

determine a virtual camera parameter associated with the digital representation;

adjust the virtual camera parameter to determine a 3D position of the corresponding patient tooth;

move the model tooth of the first 3D model from the first position to a second position, the second position corresponding to the 3D position of the corresponding patient tooth; and

generate a second 3D model comprising the model tooth of the first 3D model in the second position.