-
公开(公告)号：US20230401681A1
公开(公告)日：2023-12-14
申请号：US18236583
申请日：2023-08-22
Applicant: Google LLC
Inventor： Tiancheng Sun , Yun-Ta Tsai , Jonathan Barron
IPC: G06T5/00
CPC classification number: G06T5/008 , G06T15/506
Abstract: Apparatus and methods related to applying lighting models to images of objects are provided. A neural network can be trained to apply a lighting model to an input image. The training of the neural network can utilize confidence learning that is based on light predictions and prediction confidence values associated with lighting of the input image. A computing device can receive an input image of an object and data about a particular lighting model to be applied to the input image. The computing device can determine an output image of the object by using the trained neural network to apply the particular lighting model to the input image of the object.
-
公开(公告)号：US10237527B2
公开(公告)日：2019-03-19
申请号：US16110912
申请日：2018-08-23
Applicant: Google LLC
Inventor： Jonathan T. Barron , Yun-Ta Tsai
Abstract: A computing device may obtain an input image. The input image may have a white point represented by chrominance values that define white color in the input image. Possibly based on colors of the input image, the computing device may generate a two-dimensional chrominance histogram of the input image. The computing device may convolve the two-dimensional chrominance histogram with a filter to create a two-dimensional heat map. Entries in the two-dimensional heat map may represent respective estimates of how close respective tints corresponding to the respective entries are to the white point of the input image. The computing device may select an entry in the two-dimensional heat map that represents a particular value that is within a threshold of a maximum value in the heat map, and based on the selected entry, tint the input image to form an output image.
-
公开(公告)号：US20230360182A1
公开(公告)日：2023-11-09
申请号：US18028930
申请日：2021-05-17
Applicant: Google LLC
Inventor： Sean Ryan Francesco Fanello , Yun-Ta Tsai , Rohit Kumar Pandey , Paul Debevec , Michael Milne , Chloe LeGendre , Jonathan Tilton Barron , Christoph Rhemann , Sofien Bouaziz , Navin Padman Sarma
CPC classification number: G06T5/009 , G06T7/60 , G06T7/70 , G06T15/506 , G06T2200/24 , G06T2207/20081 , G06T2207/20084 , G06T2207/20092 , G06T2207/20208 , G06T2207/30201
Abstract: Apparatus and methods related to applying lighting models to images of objects are provided. An example method includes applying a geometry model to an input image to determine a surface orientation map indicative of a distribution of lighting on an object based on a surface geometry. The method further includes applying an environmental light estimation model to the input image to determine a direction of synthetic lighting to be applied to the input image. The method also includes applying, based on the surface orientation map and the direction of synthetic lighting, a light energy model to determine a quotient image indicative of an amount of light energy to be applied to each pixel of the input image. The method additionally includes enhancing, based on the quotient image, a portion of the input image. One or more neural networks can be trained to perform one or more of the aforementioned aspects.
-
公开(公告)号：US20230351560A1
公开(公告)日：2023-11-02
申请号：US17786841
申请日：2019-12-23
Applicant: Google LLC
Inventor： David Jacobs , Yun-Ta Tsai , Jonathan T. Barron , Xuaner Zhang
CPC classification number: G06T5/008 , G06T5/50 , G06T2207/20081 , G06T2207/30201
Abstract: Systems and methods described herein may relate to potential methods of training a machine learning model to be implemented on a mobile computing device configured to capture, adjust, and/or store image frames. An example method includes supplying a first image frame of a subject in a setting lit within a first lighting environment and supplying a second image frame of the subject lit within a second lighting environment. The method further includes determining a mask. Additionally, the method includes combining the first image frame and the second image frame according to the mask to generate a synthetic image and assigning a score to the synthetic image. The method also includes training a machine learning model based on the assigned score to adjust a captured image based on the synthetic image.
-
公开(公告)号：US10949958B2
公开(公告)日：2021-03-16
申请号：US16342911
申请日：2017-11-14
Applicant: Google LLC
Inventor： Jonathan Barron , Yun-Ta Tsai
Abstract: Methods for white-balancing images are provided. These methods include determining, for an input image, a chrominance histogram for the pixels of the input image. The determined histogram is a toroidal chrominance histogram, with an underlying, toroidal chrominance space that corresponds to a wrapped version, of a standard flat chrominance space. The toroidal chrominance histogram is- then convolved with a fitter to generate a two-dimensional heat map that is then used to determine art estimated chrominance of i|lummaiioB present id the input image; This can include fitting a bivariate von Mises distribution, or some other circular and/or toroidal, probability distribution, to the determined two-dimensional heat map. These methods for estimating illumination chrominance values for input images have reduced computational costs and increased speed relative to other methods for determining image illuminant chrominance values.
-
Patent Agency Ranking
公开(公告)号：US20180367774A1
公开(公告)日：2018-12-20
申请号：US16110912
申请日：2018-08-23
Applicant: Google LLC
Inventor： Jonathan T. Barron , Yun-Ta Tsai
CPC classification number: H04N9/735 , G06T5/001 , G06T5/20 , G06T5/40 , G06T2207/10024 , G06T2207/20016 , G06T2207/20081 , G06T2207/20084 , H04N1/6027 , H04N1/6086 , H04N9/646
Abstract: A computing device may obtain an input image. The input image may have a white point represented by chrominance values that define white color in the input image. Possibly based on colors of the input image, the computing device may generate a two-dimensional chrominance histogram of the input image. The computing device may convolve the two-dimensional chrominance histogram with a filter to create a two-dimensional heat map. Entries in the two-dimensional heat map may represent respective estimates of how close respective tints corresponding to the respective entries are to the white point of the input image. The computing device may select an entry in the two-dimensional heat map that represents a particular value that is within a threshold of a maximum value in the heat map, and based on the selected entry, tint the input image to form an output image.
-
公开(公告)号：US12136203B2
公开(公告)日：2024-11-05
申请号：US18236583
申请日：2023-08-22
Applicant: Google LLC
Inventor： Tiancheng Sun , Yun-Ta Tsai , Jonathan Barron
Abstract: Apparatus and methods related to applying lighting models to images of objects are provided. A neural network can be trained to apply a lighting model to an input image. The training of the neural network can utilize confidence learning that is based on light predictions and prediction confidence values associated with lighting of the input image. A computing device can receive an input image of an object and data about a particular lighting model to be applied to the input image. The computing device can determine an output image of the object by using the trained neural network to apply the particular lighting model to the input image of the object.
-
公开(公告)号：US12094054B2
公开(公告)日：2024-09-17
申请号：US17639967
申请日：2020-05-04
Applicant: GOOGLE LLC
Inventor： Yun-Ta Tsai , Xiuming Zhang , Jonathan T. Barron , Sean Fanello , Tiancheng Sun , Tianfan Xue
CPC classification number: G06T15/506 , G06N3/084 , G06T15/04 , G06T15/205 , G06T2200/04 , G06T2200/08 , G06T2200/24
Abstract: Examples relate to implementations of a neural light transport. A computing system may obtain data indicative of a plurality of UV texture maps and a geometry of an object. Each UV texture map depicts the object from a perspective of a plurality of perspectives. The computing system may train a neural network to learn a light transport function using the data. The light transport function may be a continuous function that specifies how light interacts with the object when the object is viewed from the plurality of perspectives. The computing system may generate an output UV texture map that depicts the object from a synthesized perspective based on an application of the light transport function by the trained neural network.
-
公开(公告)号：US20200051225A1
公开(公告)日：2020-02-13
申请号：US16342911
申请日：2017-11-14
Applicant: Google LLC
Inventor： Jonathan Barron , Yun-Ta Tsai
Abstract: Methods for white-balancing images are provided. These methods include determining, for an input image, a chrominance histogram for the pixels of the input image. The determined histogram is a toroidal chrominance histogram, with an underlying, toroidal chrominance space that corresponds to a wrapped version, of a standard flat chrominance space. The toroidal chrominance histogram is- then convolved with a fitter to generate a two-dimensional heat map that is then used to determine art estimated chrominance of i|lummaiioB present id the input image; This can include fitting a bivariate von Mises distribution, or some other circular and/or toroidal, probability distribution, to the determined two-dimensional heat map. These methods for estimating illumination chrominance values for input images have reduced computational costs and increased speed relative to other methods for determining image illuminant chrominance values,
-
公开(公告)号：US10091479B2
公开(公告)日：2018-10-02
申请号：US15703571
申请日：2017-09-13
Applicant: Google LLC
Inventor： Jonathan T. Barron , Yun-Ta Tsai
Abstract: A computing device may obtain an input image. The input image may have a white point represented by chrominance values that define white color in the input image. Possibly based on colors of the input image, the computing device may generate a two-dimensional chrominance histogram of the input image. The computing device may convolve the two-dimensional chrominance histogram with a filter to create a two-dimensional heat map. Entries in the two-dimensional heat map may represent respective estimates of how close respective tints corresponding to the respective entries are to the white point of the input image. The computing device may select an entry in the two-dimensional heat map that represents a particular value that is within a threshold of a maximum value in the heat map, and based on the selected entry, tint the input image to form an output image.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.014 seconds)
