Abstract: Techniques related to generating a virtual view of a scene from a position between positions of known input images for presentation to a viewer are discussed. Such techniques include applying a convolution mask that approximates an inverse of a linear combination of at least the horizontal and vertical convolution matrices representative of gradient detection in the input images to a virtual intermediate gradient image that is a combination of at least an interpolated virtual image at the position, an interpolated horizontal gradient map at the position, and an interpolated vertical gradient map at the position to generate a final virtual image for the position.

Abstract: Techniques related to generating a virtual view from multi-view images for presentation to a viewer are discussed. Such techniques include determining, based on a viewer position relative to a display region, first and second crop positions of planar image and cropping the planar image to a cropped planar image to fill the display region using the first and second crop positions such that the first and second crop positions define an asymmetric frustum between the cropped planar image and a virtual window corresponding to the display region.

Abstract: Techniques related to generating a virtual view of a scene from a position between positions of known input images for presentation to a viewer are discussed. Such techniques include applying a convolution mask that approximates an inverse of a linear combination of at least the horizontal and vertical convolution matrices representative of gradient detection in the input images to a virtual intermediate gradient image that is a combination of at least an interpolated virtual image at the position, an interpolated horizontal gradient map at the position, and an interpolated vertical gradient map at the position to generate a final virtual image for the position.

Abstract: Techniques related to generating a virtual view from multi-view images for presentation to a viewer are discussed. Such techniques include determining, based on a viewer position relative to a display region, first and second crop positions of planar image and cropping the planar image to a cropped planar image to fill the display region using the first and second crop positions such that the first and second crop positions define an asymmetric frustum between the cropped planar image and a virtual window corresponding to the display region.

Abstract: Systems, devices and methods are described including receiving a source image having a foreground portion and a background portion, where the background portion includes image content of a three-dimensional (3D) environment. A camera pose of the source image may be determined by comparing features of the source image to image features of target images of the 3D environment and using the camera pose to segment the foreground portion from the background portion may generate a segmented source image. The resulting segmented source image and the associated camera pose may be stored in a networked database. The camera pose and segmented source image may be used to provide a simulation of the foreground portion in a virtual 3D environment.

Abstract: A system for robust disparity estimation in the presence of significant intensity variations for camera arrays is described herein. The system comprises a camera array, a memory and a processor. The memory is configured to store imaging data. The processor is coupled to the memory and the camera array. When executing instructions, the processor is to obtain a plurality of images and generate a sequence of color matched images, wherein the sequence includes each pair of images in the plurality of images. The processor is also to calculate a plurality of disparity points based on the sequence of color matched images.

Abstract: A system for high dynamic range (HDR) imaging for camera arrays is described herein. The system includes a camera array, a memory, and a processor. The memory is configured to store imaging data from the camera array. The processor is coupled to the memory and the camera array. The processor is to obtain a plurality of images and calculate a disparity estimation of a reference image of the plurality of images. The processor is also to warp a plurality of remaining images from the plurality of images to the reference image using the disparity estimation and merge the plurality of warped remaining images and the reference image to obtain a high dynamic range image.

Abstract: A system for robust disparity estimation in the presence of significant intensity variations for camera arrays is described herein. The system comprises a camera array, a memory and a processor. The memory is configured to store imaging data. The processor is coupled to the memory and the camera array. When executing instructions, the processor is to obtain a plurality of images and generate a sequence of color matched images, wherein the sequence includes each pair of images in the plurality of images. The processor is also to calculate a plurality of disparity points based on the sequence of color matched images.

Abstract: Techniques for improved image disparity estimation are described. In one embodiment, for example, an apparatus may comprise a processor circuit and an imaging management module, and the imaging management module may be operable by the processor circuit to determine a measured horizontal disparity factor and a measured vertical disparity factor for a rectified image array, determine a composite horizontal disparity factor for the rectified image array based on the measured horizontal disparity factor and an implied horizontal disparity factor, and determine a composite vertical disparity factor for the rectified image array based on the measured vertical disparity factor and an implied vertical disparity factor. Other embodiments are described and claimed.

Abstract: Techniques for rectification of camera arrays are described. In one embodiment, for example, an apparatus may comprise a processor circuit and an imaging management module, and the imaging management module may be operable on the processor circuit to determine a composite rotation matrix for a camera array comprising a plurality of cameras, determine a composite intrinsic parameter matrix for the camera array, and compute one or more rectification maps for the camera array based on the composite rotation matrix and the composite intrinsic parameter matrix, each of the one or more rectification maps corresponding to one of the plurality of cameras. Other embodiments are described and claimed.

Abstract: Techniques for image synchronization are described herein. The techniques may include a device having logic, at least partially including hardware logic, to implement modules. The modules may include a first sync pulse module to issue a first sync pulse after a first sync pulse offset period to a first imaging sensor. The modules may also include a second sync pulse module to issue a second sync pulse parallel to the first sync pulse after a second sync pulse offset period to a second imaging sensor.

Abstract: A system, article, and method of increasing integer disparity accuracy for camera images with a diagonal layout.

Abstract: Systems and methods for determining point-to-point distances from 3D image data. In some embodiments, two measure points, for example specified by a user, represent endpoints on an object of interest within an image frame. Assuming all points lying between these endpoints also belong to the object of interest, additional 3D data associated with points that lie along a measurement line defined by the measure points may be leveraged to provide a robust distance measurement. In some embodiments, total least squares fitting is performed, for example through Robust Principal Component Analysis (RPCA) to identify linear structures within the set of the 3D coordinates on the measurement line. In some exemplary embodiments, the minimum covariance determinant (MCD) estimator of the covariance matrix of the data is computed for a highly robust estimate of multivariate location and multivariate scatter.

Abstract: Techniques for improved focusing of camera arrays are described. In one embodiment, for example, an apparatus may comprise a processor circuit and an imaging management module, and the imaging management module may be operable by the processor circuit to determine, for each of a plurality of candidate displacement factors for an image array comprising a plurality of images, a corresponding sharpness, determine an optimal displacement factor comprising a candidate displacement factor corresponding to a maximized sharpness, and transform the image array based on the optimal displacement factor. Other embodiments are described and claimed.

Abstract: Global matching of pixel data across multiple images. Pixel values of an input image are modified to better match a reference image with a slope thresholded histogram matching function. Visual artifacts are reduced by avoiding large pixel value modifications. For large intensity variations across the input and reference image, the slope of the mapping function is thresholded. Modification to the input image is therefore limited and a corresponding modification to the reference image is made to improve the image matching. More than two images may be matched by iteratively modifying a cumulative mass function of a reference image to accommodate thresholded modification of multiple input images. A device may include logic to match pixel values across a plurality of image frames generated from a plurality of image sensors on the device. Once matched, image frames may be reliably processed further for pixel correspondence, or otherwise.

Abstract: A system, article, and method of lens shift correction for a camera array.

Abstract: Techniques for improved focusing of camera arrays are described. In one embodiment, a system may include a processor circuit, a camera array, and an imaging management module for execution on the processor circuit to capture an array of images from the camera array, the array of images comprising first and second images taken with first and second values of an exposure parameter, respectively, the first value different than the second value, to estimate a noise level, to normalize an intensity of each image based upon the noise level of the respective image, to produce a respective normalized image, to identify candidate disparities in each of the respective normalized images, to estimate a high dynamic range (HDR) image patch for each candidate disparity, and to compute an error from the HDR image patch and an objective function, to produce a disparity estimate. Other embodiments are described and claimed.

Abstract: Systems and methods for determining point-to-point distances from 3D image data. In some embodiments, two measure points, for example specified by a user, represent endpoints on an object of interest within an image frame. Assuming all points lying between these endpoints also belong to the object of interest, additional 3D data associated with points that lie along a measurement line defined by the measure points may be leveraged to provide a robust distance measurement. In some embodiments, total least squares fitting is performed, for example through Robust Principal Component Analysis (RPCA) to identify linear structures within the set of the 3D coordinates on the measurement line. In some exemplary embodiments, the minimum covariance determinant (MCD) estimator of the covariance matrix of the data is computed for a highly robust estimate of multivariate location and multivariate scatter.

Abstract: Image filling utilizing image data captured by an array of cameras having different camera viewpoints. Image data, such as a pixel value or gradient value associated with a spatial point in a source region of an image is transferred to the same or another image to fill a target region. Visual artifacts may be reduced by filling portions of the target region visible from other viewpoints with expanded source patches to reduce the size of the target region to be inpainted. In embodiments, a shifted mask corresponding to the target region is determined for each supplementary image based on an estimate of foreground disparity. In further embodiments, partially occluded regions are detected based on an estimate of background disparity. Source patches may be expanded based on a baseline between camera viewpoints into large coherent regions that agree well with the target region boundary may be filled without hallucinating image data from similar patches.

Abstract: Rectification techniques for camera arrays in which the resolutions, fields of view, and/or pixel sizes of various cameras may differ from one another are described. In one embodiment, for example, an apparatus may comprise logic, at least a portion of which is in hardware, the logic to receive a captured image array captured by a heterogeneous camera array, select a rectification process for application to the captured image array, identify a set of rectification maps for the selected rectification process, and apply the identified set of rectification maps to the captured image array to obtain a rectified image array. Other embodiments are described and claimed.