公开(公告)号：US20190188535A1

公开(公告)日：2019-06-20

申请号：US15843345

申请日：2017-12-15

Applicant: Google LLC

Inventor： Jiawen Chen ,  Samuel Hasinoff ,  Michael Gharbi ,  Jonathan Barron

IPC: G06K9/62 ,  G06K9/66 ,  G06T3/40 ,  G06T3/00

CPC classification number: G06K9/6262 ,  G06K9/66 ,  G06T3/0006 ,  G06T3/4046 ,  G06T5/00 ,  G06T5/001 ,  G06T2207/20081 ,  G06T2207/20084 ,  H04N5/23293

Abstract: Systems and methods described herein may relate to image transformation utilizing a plurality of deep neural networks. An example method includes receiving, at a mobile device, a plurality of image processing parameters. The method also includes causing an image sensor of the mobile device to capture an initial image and receiving, at a coefficient prediction neural network at the mobile device, an input image based on the initial image. The method further includes determining, using the coefficient prediction neural network, an image transformation model based on the input image and at least a portion of the plurality of image processing parameters. The method additionally includes receiving, at a rendering neural network at the mobile device, the initial image and the image transformation model. Yet further, the method includes generating, by the rendering neural network, a rendered image based on the initial image, according to the image transformation model.

公开(公告)号：USD985011S1

公开(公告)日：2023-05-02

申请号：US29709053

申请日：2019-10-10

Applicant: Google LLC

Designer： Michelle Chen ,  Ryan Geiss ,  Marc Levoy ,  Kelly Tsai ,  Chorong Johnston ,  Alexander Schiffhauer ,  Samuel Hasinoff

公开(公告)号：US10579908B2

公开(公告)日：2020-03-03

申请号：US15843345

申请日：2017-12-15

Applicant: Google LLC

Inventor： Jiawen Chen ,  Samuel Hasinoff ,  Michael Gharbi ,  Jonathan Barron

IPC: G06K9/62 ,  G06K9/66 ,  G06T3/00 ,  G06T3/40 ,  G06T5/00 ,  H04N5/232

Abstract: Systems and methods described herein may relate to image transformation utilizing a plurality of deep neural networks. An example method includes receiving, at a mobile device, a plurality of image processing parameters. The method also includes causing an image sensor of the mobile device to capture an initial image and receiving, at a coefficient prediction neural network at the mobile device, an input image based on the initial image. The method further includes determining, using the coefficient prediction neural network, an image transformation model based on the input image and at least a portion of the plurality of image processing parameters. The method additionally includes receiving, at a rendering neural network at the mobile device, the initial image and the image transformation model. Yet further, the method includes generating, by the rendering neural network, a rendered image based on the initial image, according to the image transformation model.