公开(公告)号：US20210365728A1

公开(公告)日：2021-11-25

申请号：US16329893

申请日：2018-08-20

Applicant: BOE TECHNOLOGY GROUP CO., LTD

Inventor： Hanwen LIU ,  Pablo NAVARRETE MICHELINI

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: An image processing method includes: obtaining an input image; and performing image conversion processing on the input image by using a generative neural network, to output a converted output image, wherein the generative neural network includes a plurality of processing levels, wherein an output result of an i-th processing level is inputted to an (i+1)-th processing level and a j-th processing level, the j-th processing level further receives an output result of a (j−1)-th processing level, the output result of the (j−1)-th processing level and the output result of the i-th processing level have the same size, wherein i is less than j−1, i and j are positive integers.

公开(公告)号：US20200285959A1

公开(公告)日：2020-09-10

申请号：US16759669

申请日：2019-09-25

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Hanwen LIU ,  Dan ZHU ,  Pablo NAVARRETE MICHELINI

IPC: G06N3/08 ,  G06N3/04 ,  G06T3/40 ,  G06F17/16

Abstract: The present disclosure provides a training method for generative adversarial network, which includes: extracting a first-resolution sample image from a second-resolution sample image; separately providing a first input image and a second input image for a generative network to generate a first output image and a second output image respectively, the first input image including a first-resolution sample image and a first noise image, the second input image including the first-resolution sample image and a second noise image; separately providing the first output image and a second-resolution sample image for a discriminative network to output a first discrimination result and a second discrimination result; and adjusting parameters of the generative network to reduce a loss function. The present disclosure further provides an image processing method using the generative adversarial network, a computer device, and a computer-readable storage medium.

公开(公告)号：US20200034951A1

公开(公告)日：2020-01-30

申请号：US16521808

申请日：2019-07-25

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Dan ZHU ,  Pablo NAVARRETE MICHELINI ,  Hanwen LIU

IPC: G06T5/00

Abstract: An image processing method, an image processing device and a computer storage medium are provided. The method includes: performing a maximum-filtering processing on an original image and obtaining a luminance channel of the image; and performing a guided-filtering processing on the obtained luminance channel, and estimating and obtaining an incident component.

公开(公告)号：US20190220746A1

公开(公告)日：2019-07-18

申请号：US16336995

申请日：2018-08-16

Applicant: BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Hanwen LIU ,  Pablo NAVARRETE MICHELINI

IPC: G06N3/08 ,  G06N3/04 ,  G06T3/00

CPC classification number: G06N3/08 ,  G06K9/62 ,  G06N3/04 ,  G06N3/0472 ,  G06T3/0012 ,  G06T11/00

Abstract: A training method of a neural network for implementing image style transfer, an image processing method and an image processing device are disclosed. The training method includes: acquiring a first training input image and a second training input image; performing a style transfer process on the first training input image by the neural network to obtain a training output image; based on the first training input image, the second training input image and the training output image, calculating a loss value of parameters of the neural network through a loss function; and modifying the parameters of the neural network according to the loss value, where the loss function satisfies a predetermined condition, obtaining a trained neural network, where the loss function doesn't satisfy the predetermined condition, continuing to repeatedly perform above training process, the loss function including a weight-bias-ratio loss function.