中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

12 records (took 0.018 seconds)

    Methods, systems, and media for relighting images using predicted deep reflectance fields
    2.
    发明授权
    Methods, systems, and media for relighting images using predicted deep reflectance fields 有权

    公开(公告)号：US10997457B2

    公开(公告)日：2021-05-04

    申请号：US16616235

    申请日：2019-10-16

    Applicant: Google LLC

    Inventor： Christoph Rhemann ,  Abhimitra Meka ,  Matthew Whalen ,  Jessica Lynn Busch ,  Sofien Bouaziz ,  Geoffrey Douglas Harvey ,  Andrea Tagliasacchi ,  Jonathan Taylor ,  Paul Debevec ,  Peter Joseph Denny ,  Sean Ryan Francesco Fanello ,  Graham Fyffe ,  Jason Angelo Dourgarian ,  Xueming Yu ,  Adarsh Prakash Murthy Kowdle ,  Julien Pascal Christophe Valentin ,  Peter Christopher Lincoln ,  Rohit Kumar Pandey ,  Christian Häne ,  Shahram Izadi

    IPC: G06K9/46 ,  G06T15/50 ,  G06T15/20 ,  G06N3/08 ,  G06K9/62

    Abstract: Methods, systems, and media for relighting images using predicted deep reflectance fields are provided. In some embodiments, the method comprises: identifying a group of training samples, wherein each training sample includes (i) a group of one-light-at-a-time (OLAT) images that have each been captured when one light of a plurality of lights arranged on a lighting structure has been activated, (ii) a group of spherical color gradient images that have each been captured when the plurality of lights arranged on the lighting structure have been activated to each emit a particular color, and (iii) a lighting direction, wherein each image in the group of OLAT images and each of the spherical color gradient images are an image of a subject, and wherein the lighting direction indicates a relative orientation of a light to the subject; training a convolutional neural network using the group of training samples, wherein training the convolutional neural network comprises: for each training iteration in a series of training iterations and for each training sample in the group of training samples: generating an output predicted image, wherein the output predicted image is a representation of the subject associated with the training sample with lighting from the lighting direction associated with the training sample; identifying a ground-truth OLAT image included in the group of OLAT images for the training sample that corresponds to the lighting direction for the training sample; calculating a loss that indicates a perceptual difference between the output predicted image and the identified ground-truth OLAT image; and updating parameters of the convolutional neural network based on the calculated loss; identifying a test sample that includes a second group of spherical color gradient images and a second lighting direction; and generating a relit image of the subject included in each of the second group of spherical color gradient images with lighting from the second lighting direction using the trained convolutional neural network.

    METHODS, SYSTEMS, AND MEDIA FOR RELIGHTING IMAGES USING PREDICTED DEEP REFLECTANCE FIELDS
    6.
    发明申请
    METHODS, SYSTEMS, AND MEDIA FOR RELIGHTING IMAGES USING PREDICTED DEEP REFLECTANCE FIELDS 审中-公开

    公开(公告)号：US20200372284A1

    公开(公告)日：2020-11-26

    申请号：US16616235

    申请日：2019-10-16

    Applicant: Google LLC

    Inventor： Christoph Rhemann ,  Abhimitra Meka ,  Matthew Whalen ,  Jessica Lynn Busch ,  Sofien Bouaziz ,  Geoffrey Douglas Harvey ,  Andrea Tagliasacchi ,  Jonathan Taylor ,  Paul Debevec ,  Peter Joseph Denny ,  Sean Ryan Francesco Fanello ,  Graham Fyffe ,  Jason Angelo Dourgarian ,  Xueming Yu ,  Adarsh Prakash Murthy Kowdle ,  Julien Pascal Christophe Valentin ,  Peter Christopher Lincoln ,  Rohit Kumar Pandey ,  Christian Häne ,  Shahram Izadi

    IPC: G06K9/46 ,  G06T15/50 ,  G06K9/62 ,  G06N3/08 ,  G06T15/20

    Abstract: Methods, systems, and media for relighting images using predicted deep reflectance fields are provided. In some embodiments, the method comprises: identifying a group of training samples, wherein each training sample includes (i) a group of one-light-at-a-time (OLAT) images that have each been captured when one light of a plurality of lights arranged on a lighting structure has been activated, (ii) a group of spherical color gradient images that have each been captured when the plurality of lights arranged on the lighting structure have been activated to each emit a particular color, and (iii) a lighting direction, wherein each image in the group of OLAT images and each of the spherical color gradient images are an image of a subject, and wherein the lighting direction indicates a relative orientation of a light to the subject; training a convolutional neural network using the group of training samples, wherein training the convolutional neural network comprises: for each training iteration in a series of training iterations and for each training sample in the group of training samples: generating an output predicted image, wherein the output predicted image is a representation of the subject associated with the training sample with lighting from the lighting direction associated with the training sample; identifying a ground-truth OLAT image included in the group of OLAT images for the training sample that corresponds to the lighting direction for the training sample; calculating a loss that indicates a perceptual difference between the output predicted image and the identified ground-truth OLAT image; and updating parameters of the convolutional neural network based on the calculated loss; identifying a test sample that includes a second group of spherical color gradient images and a second lighting direction; and generating a relit image of the subject included in each of the second group of spherical color gradient images with lighting from the second lighting direction using the trained convolutional neural network.

    Fully parallel, low complexity approach to solving computer vision problems
    7.
    发明授权
    Fully parallel, low complexity approach to solving computer vision problems 有权

    公开(公告)号：US11037026B2

    公开(公告)日：2021-06-15

    申请号：US16749626

    申请日：2020-01-22

    Applicant: Google LLC

    Inventor： Sean Ryan Fanello ,  Julien Pascal Christophe Valentin ,  Adarsh Prakash Murthy Kowdle ,  Christoph Rhemann ,  Vladimir Tankovich ,  Philip L. Davidson ,  Shahram Izadi

    IPC: G06K9/62

    Abstract: Values of pixels in an image are mapped to a binary space using a first function that preserves characteristics of values of the pixels. Labels are iteratively assigned to the pixels in the image in parallel based on a second function. The label assigned to each pixel is determined based on values of a set of nearest-neighbor pixels. The first function is trained to map values of pixels in a set of training images to the binary space and the second function is trained to assign labels to the pixels in the set of training images. Considering only the nearest neighbors in the inference scheme results in a computational complexity that is independent of the size of the solution space and produces sufficient approximations of the true distribution when the solution for each pixel is most likely found in a small subset of the set of potential solutions.

    Fully parallel, low complexity approach to solving computer vision problems
    8.
    发明授权
    Fully parallel, low complexity approach to solving computer vision problems 有权

    公开(公告)号：US10579905B2

    公开(公告)日：2020-03-03

    申请号：US15925141

    申请日：2018-03-19

    Applicant: Google LLC

    Inventor： Sean Ryan Fanello ,  Julien Pascal Christophe Valentin ,  Adarsh Prakash Murthy Kowdle ,  Christoph Rhemann ,  Vladimir Tankovich ,  Philip L. Davidson ,  Shahram Izadi

    IPC: G06K9/62

    Abstract: Values of pixels in an image are mapped to a binary space using a first function that preserves characteristics of values of the pixels. Labels are iteratively assigned to the pixels in the image in parallel based on a second function. The label assigned to each pixel is determined based on values of a set of nearest-neighbor pixels. The first function is trained to map values of pixels in a set of training images to the binary space and the second function is trained to assign labels to the pixels in the set of training images. Considering only the nearest neighbors in the inference scheme results in a computational complexity that is independent of the size of the solution space and produces sufficient approximations of the true distribution when the solution for each pixel is most likely found in a small subset of the set of potential solutions.

Patent Agency Ranking