The present invention relates to a computer implemented method for aligning a three-dimensional model (6) of a patient's dentition to an image of the face of the patient recorded by a camera (3), the image including the mouth opening, comprising: estimating the positioning of the camera (3) relative to the face of the patient during recording of the image to obtain an estimated positioning, retrieving the three-dimensional model (6) of the dentition of the patient, rendering a two-dimensional image (7) of the dentition of the patient using the virtual camera (8) processing the three-dimensional model (6) of the dentition at the estimated positioning, carrying out feature detection in a dentition area in the mouth opening of the image (1) of the patient recorded by the camera (3) and in the rendered image (7) by performing edge detection and/or a color-based tooth likelihood determination in the respective images and forming a detected feature image for the or each detected feature, calculating a measure of deviation between the detected feature images of the image taken by the camera (3) and the detected feature image of the rendered image, varying the positioning of the virtual camera (8) to a new estimated positioning and repeating the preceding three steps in an optimization process to minimize the deviation measure to determine the best fitting positioning of the virtual camera (8).

The present invention relates to a method of determining the coherence between a physical object and a numerical model representative of the shape of a physical object, wherein a specific use of the method according to the invention is assessing and quantifying manufacturing defects. The method is characterized by a set of steps comprising: capturing multiple images of the physical object; processing the images to produce a second numerical model of the physical object; in a computer, aligning the first numerical model and the second numerical model to generate a third numerical model according to specific sub-steps, wherein the third numerical model comprises a plurality of points representative of the shape of the captured physical object. Compared with the first numerical model, the third numerical model allows determining a measurement of the coherence between the physical object captured by means of images and the first numerical model representative thereof.

Presented are concepts for adapting a first, pre-defined mesh topology representing an organ to a second, different mesh topology of the organ. One such concept includes identifying correspondence between the first and second mesh topologies based on spectral matching of the first and second mesh topologies. The first, predefined mesh topology is aligned with the second mesh topology based on the identified correspondence between the first and second mesh topologies.

A method for processing positioning data of a mobile device is provided, comprising: acquiring a first original point set and a target point set by measuring an object surface with the mobile device; extracting feature points from the first original point set to obtain an original key point set; extracting feature points from the target point set to obtain a target key point set; performing a first registration operation on the original key point set and the target key point set to obtain a first model transformation parameter; transforming the first original point set by the first model transformation parameter to obtain a second original point set; performing a second registration operation on the second original point set and the target point set to obtain a second model transformation parameter; and acquiring third model transformation parameter based on the first model transformation parameter and the second model transformation parameter.

A system for collecting data for training a computer vision model for shape estimation includes: an imaging system configured to capture one or more images; and a processing system including a processor and memory storing instructions that, when executed by the processor, cause the processor to: receive one or more input images from the imaging system; estimate a pose of an object depicted in the one or more images; render a shape estimate from a 3-D model of the object posed in accordance with the pose of the object; and generate a data point of a training dataset, the data point including one or more images based on the one or more input images and a label corresponding to the one or more images, the label including the shape estimate.

Systems and methods are provided for point cloud processing with an equivariant neural network and implicit shape learning that may produce correspondence-free registration. The systems and methods may provide for feature space preservation with the same rotation operation as a Euclidean input space, due to the equivariance property, which may provide for solving the feature-space registration in a closed form.

A method of compensating for shrinking and distortion of an object resulting from a manufacturing process. A scan is performed of an object following a manufacturing process to produce scan data. The scan data is aligned to a part mesh of the object. The part mesh is adjusted to substantially coincide with the scan data by moving part mesh vertices. Delta vectors are computed by subtracting initial part mesh vertex positions from final part mesh vertex positions. The inverse of the delta vectors are applied to the preprocessed part mesh to give a scan adjusted pre-processed shape.

For three-dimensional segmentation from two-dimensional intracardiac echocardiography imaging, the three-dimension segmentation is output by a machine-learnt multi-task generator. The machine-learnt multi-task generator is trained from 3D information, such as a sparse ICE volume assembled from the 2D ICE images. The machine-learnt multi-task generator is trained to output both the 3D segmentation and a complete volume. The 3D segmentation may be used to project to 2D as an input with an ICE image to another network trained to output a 2D segmentation for the ICE image. Display of the 3D segmentation and/or 2D segmentation may guide ablation of tissue in the patient.

A method of digitally processing a plurality of pixels of an image captured using an array of sensing pixels of an optical sensor device. The method comprises identifying a measurement pixel of the plurality of pixels corresponding to a measurement point on a target to be measured. The method then comprises identifying a number of pixels of the plurality of pixels neighbouring the measurement pixel, the number of pixels having a number of intensity values, respectively. A curve is then fitted to the number of pixels and the number of respective intensity values. An estimated intensity value is then determined from the curve in respect of the measurement pixel, thereby simulating a predetermined field of view in respect of the measurement pixel narrower than an actual field of view of the measurement pixel.

In certain embodiments, the systems, apparatus, and methods disclosed herein relate to robotic surgical systems with built-in navigation capability for patient position tracking and surgical instrument guidance during a surgical procedure, without the need for a separate navigation system. Robotic based navigation of surgical instruments during surgical procedures allows for easy registration and operative volume identification and tracking. The systems, apparatus, and methods herein allow re-registration, model updates, and operative volumes to be performed intra-operatively with minimal disruption to the surgical workflow. In certain embodiments, navigational assistance can be provided to a surgeon by displaying a surgical instrument's position relative to a patient's anatomy. Additionally, by revising pre-operatively defined data such as operative volumes, patient-robot orientation relationships, and anatomical models of the patient, a higher degree of precision and lower risk of complications and serious medical error can be achieved.