Abstract: Systems and methods for identifying tooth keypoints are disclosed. A method includes receiving digital representations comprising patient teeth, and identifying a first tooth outline from a first digital representation and a second tooth outline from a second digital representation. The method includes retrieving a 3D mesh comprising model teeth. The method includes projecting a first mesh boundary onto a patient tooth and modifying the first mesh boundary to match the first tooth outline. The method includes identifying a first tooth point on the first tooth outline that corresponds with a first mesh point on the first mesh boundary. The method includes mapping the first tooth point to the 3D mesh. The method includes determining that the first and second tooth points correspond to a common 3D mesh point. The method includes designating the first tooth point as a keypoint. The method includes modifying a digital representation based on the keypoint.

Abstract: Systems and methods for identifying tooth correspondences are disclosed. A method includes receiving a digital representation including patient teeth, and identifying a tooth outline from the digital representation. The method includes retrieving a 3D mesh including model teeth. The method includes projecting a first mesh boundary onto a patient tooth and modifying the first projected mesh boundary to match the first tooth outline. The method includes identifying a first tooth point on the first tooth outline that corresponds with a first mesh point on the first projected mesh boundary. The method includes mapping the first tooth point to the 3D mesh. The method includes determining that the first and second tooth points correspond to a common 3D mesh point. The method includes modifying at least one of the digital representation or the 3D mesh based on determining the tooth points correspond to the common 3D mesh point.

Abstract: Systems and methods for generating a 3D model of a dentition are disclosed herein. A method includes generating a first 3D model of a dentition. The dentition includes a model tooth in a first position. The method includes receiving a digital representation comprising a patient tooth. The patient tooth corresponds to the model tooth of the first 3D model. The method includes determining a virtual camera parameter associated with the digital representation. The method includes adjusting the virtual camera parameter to determine a 3D position of the corresponding patient tooth. The method includes moving the model tooth of the first 3D model from the first position to a second position. The second position corresponds to the 3D position of the corresponding patient tooth. The method includes generating a second 3D model comprising the model tooth of the first 3D model in the second position.

Abstract: Some implementations relate to methods, systems, and computer-readable media to generate text tags for games. In some implementations, a computer-implemented method to generate a 3D mesh for an object using a trained machine learning model includes providing a two-dimensional (2D) image of the object as input to the trained machine learning model, obtaining a template three-dimensional (3D) mesh, and generating, using the trained machine learning model and based on the 2D image and the template 3D mesh, a 3D mesh for the object, wherein the 3D mesh for the object is obtained by deforming the template 3D mesh and is usable to map a texture or to generate a 3D animation of the object.

Abstract: Systems and methods for generating a 3D model of a dentition are disclosed herein. A method includes generating a first 3D model of a dentition including a plurality of model teeth. The method includes receiving at least one digital representation comprising patient teeth. The method includes determining a virtual camera parameter. The virtual camera parameter corresponds with a camera used to capture the digital representation. The method includes comparing, based on the virtual camera parameter, a first position of a model tooth with a position of a corresponding patient tooth of the digital representation. The method includes moving the model tooth from the first position to a second position. The second position is based on the position of the corresponding patient tooth. The method includes generating a second 3D model comprising the model tooth of the first 3D model in the second position.

Abstract: Systems and methods for generating a three-dimensional reconstruction from a two-dimensional image of an asset are described. In some aspects, at least one computer hardware processor is used to perform: receiving a two-dimensional input image of an asset; encoding, using a first statistical model, the input image into a latent vector; and generating, using a second statistical model, at least one depth image from the latent vector, wherein pixel values in the at least one depth image correspond to coordinates of a point cloud.

Abstract: Some implementations relate to methods, systems, and computer-readable media to generate 3D assets from 2D images. In some implementations, a computer-implemented method to generate a 3D asset for an object using a trained machine learning model includes providing a 2D image of the object as input to the trained machine learning model, obtaining a template 3D mesh and a representative of a class of objects of interest that includes the object, generating based on the template 3D mesh and the representative of the class, a rigged 3D mesh for the object, deforming and posing the rigged 3D mesh to match the 2D image, and applying a texture extracted from the 2D image to the deformed and posed 3D mesh to create the 3D asset of the object.

Abstract: Some implementations relate to methods, systems, and computer-readable media to generate 3D assets from 2D images. In some implementations, a computer-implemented method to generate a 3D asset for an object using a trained machine learning model includes providing a 2D image of the object as input to the trained machine learning model, obtaining a template 3D mesh and a representative of a class of objects of interest that includes the object, generating based on the template 3D mesh and the representative of the class, a rigged 3D mesh for the object, deforming and posing the rigged 3D mesh to match the 2D image, and applying a texture extracted from the 2D image to the deformed and posed 3D mesh to create the 3D asset of the object.

Abstract: Systems and methods for generating a three-dimensional reconstruction from a two-dimensional image of an asset are described. In some aspects, at least one computer hardware processor is used to perform: receiving a two-dimensional input image of an asset; encoding, using a first statistical model, the input image into a latent vector; and generating, using a second statistical model, at least one depth image from the latent vector, wherein pixel values in the at least one depth image correspond to coordinates of a point cloud.

Abstract: Some implementations relate to methods, systems, and computer-readable media to generate text tags for games. In some implementations, a computer-implemented method to generate a 3D mesh for an object using a trained machine learning model includes providing a two-dimensional (2D) image of the object as input to the trained machine learning model, obtaining a template three-dimensional (3D) mesh, and generating, using the trained machine learning model and based on the 2D image and the template 3D mesh, a 3D mesh for the object, wherein the 3D mesh for the object is obtained by deforming the template 3D mesh and is usable to map a texture or to generate a 3D animation of the object.

Abstract: Systems and methods for generating a three-dimensional reconstruction from a two-dimensional image of an asset are described. In some aspects, at least one computer hardware processor is used to perform: receiving a two-dimensional input image of an asset; encoding, using a first statistical model, the input image into a latent vector; and generating, using a second statistical model, at least one depth image from the latent vector, wherein pixel values in the at least one depth image correspond to coordinates of a point cloud.