Abstract: Techniques and apparatuses for highlighting media through weighting of people or contexts are described. This document describes techniques that allow a user to quickly and easily highlight media, such as through generating a highlight reel. The techniques also enable selection of context and person weightings by which to tailor highlight reels.

Abstract: Techniques and apparatuses for highlighting media through weighting of people or contexts are described. This document describes techniques that allow a user to quickly and easily highlight media, such as through generating a highlight reel. The techniques also enable selection of context and person weightings by which to tailor highlight reels.

Abstract: Techniques and apparatuses for highlighting media through weighting of people or contexts are described. This document describes techniques that allow a user to quickly and easily highlight media, such as through generating a highlight reel. The techniques also enable selection of context and person weightings by which to tailor highlight reels.

Abstract: Techniques and apparatuses for highlighting media through weighting of people or contexts are described. This document describes techniques that allow a user to quickly and easily highlight media, such as through generating a highlight reel. The techniques also enable selection of context and person weightings by which to tailor highlight reels.

Abstract: The embodiments described herein perform image infusion on Bayer image data that is coordinated with Clear image data captured with a dual camera. A first image sensor of the dual camera captures a Bayer image, while a second sensor captures a Clear image, where the first sensor and the second sensor are synchronized to capture the images at the same time. Some embodiments generate a relational mapping of Clear luma channel data extracted from the Clear image to Bayer luma channel data extracted from the Bayer image data, and use the relational mapping to generate multiple de-noised luma representations associated with the Bayer image. The multiple de-noised luma representations are then selectively merged together to generate a resultant image that retains a high signal-to-noise radio (SNR) and reduces artifacts obtained by the image processing.

Abstract: Techniques and apparatuses for generating highlight reels are described. These techniques and apparatuses enable a user to quickly and easily generate a highlight reel to highlight audiovisual media, such as photos and video clips.

Abstract: Techniques and apparatuses for generating highlight reels are described. These techniques and apparatuses enable a user to quickly and easily generate a highlight reel to highlight audiovisual media, such as photos and video clips.

Abstract: A camera device includes monochromatic and color image sensors that capture an image as a clear image in monochrome and as a Bayer image. The camera device implements image processing algorithms to produce an enhanced, high-resolution HDR color image. The Bayer image is demosaiced to generate an initial color image, and a disparity map is generated to establish correspondence between pixels of the initial color image and clear image. A mapped color image is generated to map the initial color image onto the clear image. A denoised clear image is applied as a guide image of a guided filter that filters the mapped color image to generate a filtered color image. The filtered color image and the denoised clear image are then fused to produce an enhanced, high-resolution HDR color image, and the disparity map and the mapped color image are updated based on the enhanced, high-resolution HDR color image.

Abstract: Gathering a plurality of sequential image sets from a scene. The sets include a main sequential image set and one or more additional sequential image sets. The main sequential image set includes a main central image that is near a temporal midpoint of the set, and one or more remaining main images. The additional sequential image sets each include a plurality of additional images comprising an additional central image and one or more additional remaining images. The one or more remaining main images and the plurality of additional images are used to perform filtering of the main central image to provide a filtered main central image having an enhanced signal-to-noise ratio.

Abstract: Techniques apparatuses for grading images and video clips are described. These techniques and apparatuses enable highlights of these graded images and video clips to be more-quickly created, at a high quality, or using fewer resources.

Abstract: In embodiments, a camera device includes HDR monochromatic image sensors that capture an image as an HDR clear image in monochrome, and the camera device includes HDR color image sensors that capture the image as a Bayer image. The HDR monochromatic image sensors may be implemented as interlaced pixel lines having alternating higher exposure times and lower exposure times, or may be implemented as a checkerboard pixel pattern with white pixels of the checkerboard pixel pattern having an exposure duration and black pixels of the checkerboard pixel pattern having a different exposure duration. The camera device implements image processing algorithms that demosaic the Bayer image to generate an initial color image, and demosaic the HDR clear image to generate a clear image. An image fusion application then produces an enhanced, high-resolution HDR color image based on the initial color image and the clear image.

Abstract: A camera device includes monochromatic and color image sensors that capture an image as a clear image in monochrome and as a Bayer image. The camera device implements image processing algorithms to produce an enhanced, high-resolution HDR color image. The Bayer image is demosaiced to generate an initial color image, and a disparity map is generated to establish correspondence between pixels of the initial color image and clear image. A mapped color image is generated to map the initial color image onto the clear image. A denoised clear image is applied as a guide image of a guided filter that filters the mapped color image to generate a filtered color image. The filtered color image and the denoised clear image are then fused to produce an enhanced, high-resolution HDR color image, and the disparity map and the mapped color image are updated based on the enhanced, high-resolution HDR color image.

Abstract: In embodiments, a camera device includes HDR monochromatic image sensors that capture an image as an HDR clear image in monochrome, and the camera device includes HDR color image sensors that capture the image as a Bayer image. The HDR monochromatic image sensors may be implemented as interlaced pixel lines having alternating higher exposure times and lower exposure times, or may be implemented as a checkerboard pixel pattern with white pixels of the checkerboard pixel pattern having an exposure duration and black pixels of the checkerboard pixel pattern having a different exposure duration. The camera device implements image processing algorithms that demosaic the Bayer image to generate an initial color image, and demosaic the HDR clear image to generate a clear image. An image fusion application then produces an enhanced, high-resolution HDR color image based on the initial color image and the clear image.

Abstract: This document describes techniques that allow a user to quickly and easily share visual media. In some cases the techniques share visual media with an interested person automatically and without needing interaction from the user, such as to select the person or the manner in which to share an image. Further, the interested person need not be in the visual media, instead, the interested person can simply be someone that has a previously established interest in a person or object that is within the visual media.

Abstract: Techniques and apparatuses for sharing highlight reels are described. This document describes techniques that allow a user to quickly and easily generate a highlight reel. The techniques also enable sharing of these highlight reels, in some cases automatically on creating the highlight reel, such as to persons known to be shown in the highlight reel.

Abstract: Techniques and apparatuses for generating highlight reels are described. These techniques and apparatuses enable a user to quickly and easily generate a highlight reel to highlight audiovisual media, such as photos and video clips.

Abstract: Techniques and apparatuses for highlighting media through weighting of people or contexts are described. This document describes techniques that allow a user to quickly and easily highlight media, such as through generating a highlight reel. The techniques also enable selection of context and person weightings by which to tailor highlight reels.

Abstract: Techniques apparatuses for grading images and video clips are described. These techniques and apparatuses enable highlights of these graded images and video clips to be more-quickly created, at a high quality, or using fewer resources.

Abstract: This document describes techniques and apparatuses for implementing an asymmetric sensor array for capturing images. These techniques and apparatuses enable better resolution, depth of color, or low-light sensitivity than many conventional sensor arrays.

Abstract: A method to recognize a facial image is described. An input facial image is normalized by scaling and rotation angle using methods of eye pupil centers detection. The input facial image is further normalized by lighting intensity. Template images are obtained either by the processing of certain images taken from different face positions, or by a preliminary reconstruction of a 3D face model based on stereo-pair images. Using the 3D model template, facial images are generated at different rotation angles. Distances between the input facial image and the template image are calculated from the Discrete Cosine Transformation (DCT) features, defined by overlapped blocks of these images. The facial image is recognized based on these distances.