公开(公告)号：US11368669B2

公开(公告)日：2022-06-21

申请号：US17133271

申请日：2020-12-23

Applicant: Intel Corporation

Inventor： Fan Zhang ,  Oscar Nestares

IPC: H04N13/344 ,  G06T3/00 ,  H04N5/232 ,  H04N13/296 ,  H04N13/398 ,  G06T3/40 ,  G06T15/00

Abstract: An example system for generating stereoscopic light field panoramas includes at least one memory; and at least one processor to execute instructions to: access images of a scene captured by a plurality of cameras, the images including light field information associated with the scene; generate, based on first portions of the images, a first stereoscopic light field panorama for a first perspective associated with a left eye viewpoint of the scene, the left eye viewpoint associated with a left eye position on a first circle; and generate, based on second portions of the images, a second stereoscopic light field panorama for a second perspective associated with a right eye viewpoint of the scene, the right eye viewpoint associated with a right eye position on a second circle, the first circle being different than and concentric to the second circle.

公开(公告)号：US11009764B2

公开(公告)日：2021-05-18

申请号：US15860584

申请日：2018-01-02

Applicant: Intel Corporation

Inventor： Jun Jiang ,  Zhiming Zhuang ,  Ginni Grover ,  Basel Salahieh ,  Oscar Nestares ,  David W. Browning

IPC: G02F1/29 ,  G02B27/01

Abstract: Technology for improving performance of a personal display device by variably controlling the emission divergence and/or the emission direction of light from the pixels of the display as a function of the location of the pixel within a display.

公开(公告)号：US20210120225A1

公开(公告)日：2021-04-22

申请号：US17133271

申请日：2020-12-23

Applicant: Intel Corporation

Inventor： Fan Zhang ,  Oscar Nestares

IPC: H04N13/344 ,  G06T3/00 ,  H04N5/232 ,  H04N13/296 ,  H04N13/398 ,  G06T3/40 ,  G06T15/00

Abstract: An example system for generating stereoscopic light field panoramas includes at least one memory; and at least one processor to execute instructions to: access images of a scene captured by a plurality of cameras, the images including light field information associated with the scene; generate, based on first portions of the images, a first stereoscopic light field panorama for a first perspective associated with a left eye viewpoint of the scene, the left eye viewpoint associated with a left eye position on a first circle; and generate, based on second portions of the images, a second stereoscopic light field panorama for a second perspective associated with a right eye viewpoint of the scene, the right eye viewpoint associated with a right eye position on a second circle, the first circle being different than and concentric to the second circle.

公开(公告)号：US20210004969A1

公开(公告)日：2021-01-07

申请号：US17029896

申请日：2020-09-23

Applicant: Intel Corporation

Inventor： Niloufar Pourian ,  Oscar Nestares

IPC: G06T7/269

Abstract: Techniques related to multi-level optical flow estimation are discussed. Such techniques include partitioning each pair of input images into one or more partitions, separately performing optical flow estimation on the partitions, and merging the separately generated optical flow results into a final optical flow map for the pair of input images.

公开(公告)号：US20190220963A1

公开(公告)日：2019-07-18

申请号：US16365539

申请日：2019-03-26

Applicant: Intel Corporation

Inventor： Vladan Popovic ,  Fan Zhang ,  Oscar Nestares ,  Kalpana Seshadrinathan

IPC: G06T5/20 ,  G06T3/40 ,  G06T5/50 ,  G06T7/00

CPC classification number: G06T5/20 ,  G06T3/4007 ,  G06T5/50 ,  G06T7/0002

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.

公开(公告)号：US10063840B2

公开(公告)日：2018-08-28

申请号：US14660843

申请日：2015-03-17

Applicant: INTEL CORPORATION

Inventor： Gowri Somanath ,  Oscar Nestares

IPC: H04N13/00 ,  H04N13/02 ,  G06K9/00 ,  G06K9/62

CPC classification number: H04N13/243 ,  G06K9/00214 ,  G06K9/6201 ,  G06K2009/6213 ,  G06T7/593

Abstract: A system, article, and method of sub-pixel accuracy 3D measurement using multiple images.

公开(公告)号：US20180198970A1

公开(公告)日：2018-07-12

申请号：US15404759

申请日：2017-01-12

Applicant: INTEL CORPORATION

Inventor： Kalpana Seshadrinathan ,  Oscar Nestares

IPC: H04N5/235 ,  H04N5/225 ,  G06T3/00 ,  G06T11/60 ,  H04N9/04 ,  G06T7/90 ,  G06K9/62

CPC classification number: H04N5/2355 ,  G06T3/0093 ,  G06T5/009 ,  G06T5/50 ,  G06T7/33 ,  G06T2200/21 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10144 ,  G06T2207/20208 ,  G06T2207/20221 ,  H04N5/2258 ,  H04N5/2356 ,  H04N5/247 ,  H04N5/2628

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.

公开(公告)号：US09922681B2

公开(公告)日：2018-03-20

申请号：US15142475

申请日：2016-04-29

Applicant: INTEL CORPORATION

Inventor： Daniel C. Middleton ,  Oscar Nestares ,  Lucas B. Ainsworth

IPC: G11B27/031

CPC classification number: G11B27/031

Abstract: Techniques are disclosed for adding interactive features to videos to enable users to create new media using a dynamic blend of motion and still imagery. The interactive techniques can include allowing a user to change the starting time of one or more subjects in a given video frame, or only animate/play a portion of a given frame scene. The techniques may include segmenting each frame of a video to identify one or more subjects within each frame, selecting (or receiving selections of) one or more subjects within the given frame scene, tracking the selected subject(s) from frame to frame, and alpha-matting to play/animate only the selected subject(s). In some instances, segmentation, selection, and/or tracking may be improved and/or enhanced using pixel depth information (e.g., using a depth map).

公开(公告)号：US09792687B2

公开(公告)日：2017-10-17

申请号：US14841609

申请日：2015-08-31

Applicant: Intel Corporation

Inventor： Kalpana Seshadrinathan ,  Oscar Nestares ,  Ali Mehdizadeh ,  Max T. Stein ,  Yi Wu ,  James Granger

IPC: G06T7/00 ,  G01B11/14 ,  H04N5/247

CPC classification number: G06T7/62 ,  G01B11/14 ,  G06T2207/10012 ,  G06T2207/10028 ,  H04N5/247

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.

公开(公告)号：US09712720B2

公开(公告)日：2017-07-18

申请号：US14293611

申请日：2014-06-02

Applicant: Intel Corporation

Inventor： Oscar Nestares ,  Yong Jiang

IPC: G06K9/00 ,  H04N1/60 ,  G06T5/00 ,  G06T5/50 ,  H04N5/232 ,  H04N5/247 ,  H04N1/409

CPC classification number: H04N1/6027 ,  G06T5/003 ,  G06T5/20 ,  G06T5/50 ,  G06T2207/10052 ,  G06T2207/20016 ,  G06T2207/20224 ,  H04N1/409 ,  H04N5/23229 ,  H04N5/247

Abstract: Techniques related to image refocusing for camera arrays using a space variant filter based on a pixel by pixel blur level associated with a difference between a reference image and a basic refocused image are discussed. Such techniques may include taking the difference between the reference image and the basic refocused image and applying a space variant filter to the basic refocused image to generate a final refocused image having a region of increased blur with respect to the all in focus reference image. The blur level implemented by the space variant filter may be based on the difference and, optionally, the reference image noise level and the reference image gradient.