公开(公告)号：US20230385990A1

公开(公告)日：2023-11-30

申请号：US18227120

申请日：2023-07-27

Applicant: Google LLC

Inventor： Chitwan Saharia ,  Jonathan Ho ,  William Chan ,  Tim Salimans ,  David Fleet ,  Mohammad Norouzi

IPC: G06T5/00 ,  G06T5/50 ,  G06T3/40 ,  G06N3/08 ,  G06N3/045

CPC classification number: G06T5/002 ,  G06T5/50 ,  G06T3/4007 ,  G06N3/08 ,  G06N3/045 ,  G06T2207/20081 ,  G06T2207/20016 ,  G06T2207/20084

Abstract: A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.

公开(公告)号：US11769228B2

公开(公告)日：2023-09-26

申请号：US17391150

申请日：2021-08-02

Applicant: Google LLC

Inventor： Chitwan Saharia ,  Jonathan Ho ,  William Chan ,  Tim Salimans ,  David Fleet ,  Mohammad Norouzi

IPC: G06T5/00 ,  G06T5/50 ,  G06T3/40 ,  G06N3/08 ,  G06N3/045

CPC classification number: G06T5/002 ,  G06N3/045 ,  G06N3/08 ,  G06T3/4007 ,  G06T5/50 ,  G06T2207/20016 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.

公开(公告)号：US11756166B2

公开(公告)日：2023-09-12

申请号：US18155420

申请日：2023-01-17

Applicant: Google LLC

Inventor： Chitwan Saharia ,  Jonathan Ho ,  William Chan ,  Tim Salimans ,  David Fleet ,  Mohammad Norouzi

IPC: G06T5/00 ,  G06N3/08 ,  G06T5/50 ,  G06N3/045 ,  G06T3/40

CPC classification number: G06T5/002 ,  G06N3/045 ,  G06N3/08 ,  G06T3/4007 ,  G06T5/50 ,  G06T2207/20016 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.

公开(公告)号：US20230067841A1

公开(公告)日：2023-03-02

申请号：US17391150

申请日：2021-08-02

Applicant: Google LLC

Inventor： Chitwan Saharia ,  Jonathan Ho ,  William Chan ,  Tim Salimans ,  David Fleet ,  Mohammad Norouzi

IPC: G06T5/00 ,  G06T5/50 ,  G06T3/40 ,  G06N3/08 ,  G06N3/04

Abstract: A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.