Resulting from a reduction in the accuracy of a feature point obtained from a viewpoint inclined with respect to the front direction of an object, the estimation accuracy of three-dimensional coordinates of the feature point is reduced. Consequently, from each of a plurality of images captured from a plurality of viewpoints, the feature point of the object is detected and attribute information indicating which area of the object the detected feature point belongs to is appended to the detected feature point. Then, for each of the same attribute information, the three-dimensional coordinates of the feature point are calculated by using two-dimensional coordinates of the feature point on the image corresponding to the viewpoints not more than the plurality of viewpoints and not less than two.

A deep neural network based hair rendering system is presented to model high frequency component of furry objects. Compared with existing approaches, the present method can generate photo-realistic rendering results. An acceleration method is applied in our framework, which can speed up training and rendering processes. In addition, a patch-based training scheme is introduced, which significantly increases the quality of outputs and preserves high frequency details.

A method of determining a depth of a hole milled into a first region of a sample, comprising: positioning the sample in a processing chamber having a charged particle beam column; milling a hole in the first region of the sample using a charged particle beam generated by the charged particle beam column; identifying a first registration mark at an upper level of the milled hole; identifying a second registration mark at a lower level of the milled hole; taking a first set of images at a first tilt angle, the first set of images including a first image taken with a field of view that captures the first registration mark but not the second registration mark, and a second image taken with a field of view that captures the second registration mark but not the first registration mark; taking a second set of images at a second tilt angle, different than the first tilt angle, the second set of images including a third image taken with a field of view that captures the first registration mark but not the second registration mark, and a fourth image taken with a field of view that captures the second registration mark but not the first registration mark; using stereoscopic measurement techniques to determine the depth of the hole based on the first and second sets of images.

A visual guidance system for use in a surgical procedure include a calibration operation of a tip of a surgical drill. In particular, the system includes capturing images of a drill tip and generating a reconstruction volume shape of the drill tip to enable tracking of the drill tip. The system captures images of the drill tip in tilting motion to determine cutting edge contour data of the drill tip. The system further captures images of the drill tip in rotation and identifies point cloud data of the drill tip. The system further includes generating a three-dimensional surface data of the drill tip, a cutting plane, and a cutting edge contour of the drill tip. Given the three dimensional surface data and plane data, the system further generates guidance data for providing a navigation on surgical procedure using three-dimensional graphical representation of the surgical drill.

A multi-modal stereo vision system includes one or more stereo vision units. Each stereo vision unit includes a plurality of stereo camera pairs. Each image pair includes a first image and a second image. The plurality of stereo camera pairs can capture multi-modal image data.

A method and apparatus for sorting is described, and which includes providing a product stream formed of individual objects of interest having feature aspects which can be detected; generating multiple images of each of the respective objects of interest; classifying the feature aspects of the objects of interest; identifying complementary images by analyzing some of the multiplicity of images; fusing the complementary images to form an aggregated region representation of the complementary images; and sorting the respective objects of interest based at least in part upon the aggregated region representation which is formed.

An electronic apparatus and a method for controlling thereof are provided. The electronic apparatus includes a first display comprising a first display panel for displaying a multi-view image and a micro-lens array which is arranged on a front surface of the first display panel and is for adjusting directions of lights output through the first display panel, a second display comprising a second display panel which is arranged on the front surface of the first display and displays a two-dimensional image corresponding to the multi-view image and has a transmittance greater than or equal to a predetermined value, memory storing one or more computer program, and one or more processors communicatively coupled to the first display, the second display, and the memory.

An electronic apparatus and a method for controlling thereof are provided. The electronic apparatus includes a first display comprising a first display panel for displaying a multi-view image and a micro-lens array which is arranged on a front surface of the first display panel and is for adjusting directions of lights output through the first display panel, a second display comprising a second display panel which is arranged on the front surface of the first display and displays a two-dimensional image corresponding to the multi-view image and has a transmittance greater than or equal to a predetermined value, memory storing one or more computer program, and one or more processors communicatively coupled to the first display, the second display, and the memory.

Systems and methods for estimating depth from projected texture using camera arrays are described. A camera array includes a conventional camera and at least one two-dimensional array of cameras, where the conventional camera has a higher resolution than the cameras in the at least one two-dimensional array of cameras, an illumination system configured to illuminate a scene with a projected texture, where an image processing pipeline application directs the processor to: utilize the illumination system controller application to control the illumination system to illuminate a scene with a projected texture, capture a set of images of the scene illuminated with the projected texture, and determining depth estimates for pixel locations in an image from a reference viewpoint using at least a subset of the set of images.

A visual guidance system for use in a surgical procedure include a calibration operation of a tip of a surgical drill. In particular, the system includes capturing images of a drill tip and generating a reconstruction volume shape of the drill tip to enable tracking of the drill tip. The system captures images of the drill tip in tilting motion to determine cutting edge contour data of the drill tip. The system further captures images of the drill tip in rotation and identifies point cloud data of the drill tip. The system further includes generating a three-dimensional surface data of the drill tip, a cutting plane, and a cutting edge contour of the drill tip. Given the three dimensional surface data and plane data, the system further generates guidance data for providing a navigation on surgical procedure using three-dimensional graphical representation of the surgical drill.