Dental scanning system with structured light projection

A dental scanning system for generating a digital three-dimensional (3D) representation of a dental object, the dental scanning system comprising:

• a handheld intraoral scanner comprising:
• one or more light projectors configured to project a checkerboard pattern of light onto a surface of the dental object, wherein each light projector comprises at least one light source configured to generate unpatterned light and a pattern generating optical element configured to receive the unpatterned light and to generate the checkerboard pattern of light based on propagation of the unpatterned light through the pattern generating optical element, wherein the pattern generating optical element comprises a transmission mask, wherein the at least one light source comprises at least one light emitting diode, wherein the checkerboard pattern of light comprises a plurality of pattern features, and wherein each pattern feature of the plurality of pattern features is defined by one or more projector rays;
• and
• two or more cameras configured to acquire one or more sets of images, each of the two or more cameras comprising a camera sensor having an array of pixels, wherein each set of images comprises at least one image from each camera, wherein each image includes one or more image features of at least a portion of the projected checkerboard pattern of light;
• and
• one or more processors configured to:
• for each set of images, determine a correspondence between pattern features in the checkerboard pattern of light and image features in the set of images by determining, in a 3D space, intersections of projector rays corresponding to one or more of the plurality of pattern features and camera rays corresponding to the one or more image features based on calibration data that associates the camera rays corresponding to pixels on the camera sensor of each of the two or more cameras to the projector rays, wherein determining the correspondence comprises:
• determining, for a first subset of the pattern features that are associated with a highest number of image features, a first correspondence between the first subset of the pattern features and first image features in the 3D space;
• and
• subsequently determining, for a second subset of the pattern features that are associated with a next highest number of image features, a second correspondence between the second subset of the pattern features and second image features in the 3D space;
• and
• generate the digital 3D representation of the dental object based on the determined correspondence between the pattern features and the image features in the one or more sets of images.

A dental scanning system for generating a digital three-dimensional (3D) representation of a dental object, the dental scanning system comprising:

• a handheld intraoral scanner comprising:
• one or more light projectors configured to project a pattern of light onto a surface of the dental object, wherein the pattern of light comprises a plurality of pattern features, and wherein each pattern feature of the plurality of pattern features is defined by one or more projector rays;
• and
• two or more cameras configured to acquire one or more sets of images, each of the two or more cameras comprising a camera sensor having an array of pixels, wherein each set of images comprises at least one image from each camera, wherein each image includes one or more image features of at least a portion of the projected pattern of light, and wherein the images within a set of images are acquired simultaneously;
• and
• one or more processors configured to:
• for each set of images, determine a correspondence between pattern features in the pattern of light and image features in the set of images by determining, in a 3D space, intersections of projector rays corresponding to one or more of the plurality of pattern features and camera rays corresponding to the one or more image features based on calibration data that associates the camera rays corresponding to pixels on the camera sensor of each of the two or more cameras to the projector rays, wherein each projector ray corresponds to a respective path of pixels on the camera sensor of a respective one of the two or more cameras, and wherein to determine the intersections of the projector rays and the camera rays in three-dimensional (3D) space the one or more processors are further to run a correspondence algorithm to:
• for each projector ray i, identify for each detected image feature j on a camera sensor path corresponding to projector ray i, how many other cameras, on their respective camera sensor paths corresponding to projector ray i, detected respective image features k corresponding to respective camera rays that intersect projector ray i and a camera ray corresponding to detected image feature j, wherein projector ray i is identified as a specific projector ray that produced a detected image feature j for which the highest number of other cameras detected respective image features k;
• and
• compute a respective three-dimensional position on the dental object at an intersection of projector ray i and the respective camera rays corresponding to the detected image feature j and the respective detected image features k;
• and
• generate the digital 3D representation of the dental object based on the determined correspondence between the pattern features and the image features in the one or more sets of images.

A dental scanning system for generating a digital three-dimensional (3D) representation of a dental object, the dental scanning system comprising:

• a handheld intraoral scanner comprising:
• one or more light projectors configured to project a pattern of light onto a surface of the dental object, wherein the pattern of light comprises a plurality of pattern features, and wherein each pattern feature of the plurality of pattern features is defined by one or more projector rays;
• and
• two or more cameras configured to acquire one or more sets of images, each of the two or more cameras comprising a camera sensor having an array of pixels, wherein each set of images comprises at least one image from each camera, wherein each image includes one or more image features of at least a portion of the projected pattern of light;
• and
• one or more processors configured to:
• for each set of images, determine a correspondence between pattern features in the pattern of light and image features in the set of images by determining, in a 3D space, intersections of projector rays corresponding to one or more of the plurality of pattern features and camera rays corresponding to the one or more image features based on calibration data that associates the camera rays corresponding to pixels on the camera sensor of each of the two or more cameras to the projector rays, wherein determining the correspondence comprises:
• detecting the one or more image features in the one or more sets of images using a neural network
• determining, for a first subset of the pattern features that are associated with a highest number of image features, a first correspondence between the first subset of the pattern features and first image features in the 3D space;
• and
• subsequently determining, for a second subset of the pattern features that are associated with a next highest number of image features, a second correspondence between the second subset of the pattern features and second image features in the 3D space;
• and
• generate the digital 3D representation of the dental object based on the determined correspondence between the pattern features and the image features in the one or more sets of images.

A dental scanning system for generating a digital three-dimensional (3D) representation of a dental object, the dental scanning system comprising:

• a handheld intraoral scanner comprising:
• one or more light projectors configured to project a pattern of light onto a surface of a dental object, wherein the pattern of light comprises a plurality of pattern features, and wherein each pattern feature of the plurality of pattern features is defined by one or more projector rays;
• and
• one or more cameras configured to acquire one or more sets of images, each of the one or more cameras comprising a camera sensor having an array of pixels, wherein each set of images comprises at least one image from each camera, wherein each image includes one or more image features of at least a portion of the projected pattern of light, and wherein the images within a set of images are acquired simultaneously;
• a mirror at a distal end of a probe of the intraoral scanning device, wherein a light projector of the one or more light projectors and a camera of the one or more cameras are positioned to face the mirror, and wherein the mirror is positioned to reflect the pattern of light onto the dental object and to reflect the pattern of light from the dental object into the camera;
• and
• one or more processors configured to:
• for each set of images, determine a correspondence between pattern features in the pattern of light and image features in the set of images by determining, in a three-dimensional (3D) space, intersections of projector rays corresponding to one or more of the plurality of pattern features and camera rays corresponding to the one or more image features based on calibration data that associates the camera rays corresponding to pixels on the camera sensor of each of the one or more cameras to the projector rays, wherein determining the correspondence comprises:
• determining, for a first subset of the pattern features that are associated with a highest number of image features, a first correspondence between the first subset of the pattern features and first image features in the 3D space;
• and
• subsequently determining, for a second subset of the pattern features that are associated with a next highest number of image features, a second correspondence between the second subset of the pattern features and second image features in the 3D space;
• and
• generate the digital 3D representation of the dental object based on the determined correspondence between the pattern features and the image features in the one or more sets of images.