利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

22 条记录 (耗时 0.022 秒)

    Object Observation Tracking In Images Using Encoder-Decoder Models
    2.
    发明申请
    Object Observation Tracking In Images Using Encoder-Decoder Models 有权

    公开(公告)号：US20220405569A1

    公开(公告)日：2022-12-22

    申请号：US17304505

    申请日：2021-06-22

    申请人： Google LLC

    发明人： Onur G. Guleryuz ,  Sean Ryan Francesco Fanello

    IPC分类号： G06N3/08 ,  G06F3/01 ,  G06K9/00 ,  G06N3/04

    摘要： A method including, in a training phase, training a gaze prediction model including a first model and a second model, the first model and the second model being configured in conjunction to predict segmentation data based on training data, training a third model together with the first model and the second model, the third model being configured to predict a training characteristic using an output of the first model based on the training data, and in an operational phase, receiving operational data and predicting an operational characteristic using the trained first model and the trained third model.

    Methods, systems, and media for relighting images using predicted deep reflectance fields
    8.
    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

    申请人： Google LLC

    发明人： 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分类号： G06K9/46 ,  G06T15/50 ,  G06T15/20 ,  G06N3/08 ,  G06K9/62

    摘要： 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.