公开(公告)号：US20210326691A1

公开(公告)日：2021-10-21

申请号：US16492873

申请日：2019-03-22

Applicant: BOE Technology Group Co., Ltd.

Inventor： Hanwen Liu ,  Pablo Navarrete Michelini ,  Lijie Zhang ,  Dan Zhu

IPC: G06N3/08 ,  G06K9/62 ,  G06T3/40

Abstract: A computer-implemented method using a convolutional neural network is provided. The computer-implemented method using a convolutional neural network includes processing an input image through at least one channel of the convolutional neural network to generate an output image including content features of the input image morphed with style features of a reference style image. The at least one channel includes a down-sampling segment, a densely connected segment, and an up-sampling segment sequentially connected together. Processing the input image through the at least one channel of the convolutional neural network includes processing an input signal through the down-sampling segment to generate a down-sampling segment output; processing the down-sampling segment output through the densely connected segment to generate a densely connected segment output; and processing the densely connected segment output through the up-sampling segment to generate an up-sampling segment output. The input signal includes a component of the input image.

公开(公告)号：US10706504B2

公开(公告)日：2020-07-07

申请号：US15921961

申请日：2018-03-15

Applicant: BOE Technology Group Co., Ltd.

Inventor： Hanwen Liu ,  Pablo Navarrete Michelini

IPC: G06K9/62 ,  G06T3/40 ,  G06T5/10 ,  G06T5/00 ,  G06N3/02

Abstract: The embodiments of the present disclosure provide an image processing method, and a processing device. The image processing method comprises: acquiring a first image including N components, where N is a positive integer greater than or equal to 1; and performing image conversion processing on the first image using a generative neural network, to output a first output image, wherein the generative neural network is trained using a Laplace transform function.

公开(公告)号：US20190139193A1

公开(公告)日：2019-05-09

申请号：US15936862

申请日：2018-03-27

Applicant: BOE Technology Group Co, Ltd

Inventor： Pablo Navarrete Michelini ,  Hanwen Liu

IPC: G06T3/40

Abstract: An image processing apparatus and method, an image processing system and a training method are disclosed. The image processing method comprises: receiving an input image; and inputting the input image to K stages of cascaded decoding units, to process the input image to obtain an output image, wherein an ith stage of decoding unit receives mK+1−i input images and outputs mK−i output images, a resolution of the output images is greater than a resolution of the input images, and the number of image components of the output images is less than the number of image components of the input images, where K, i and m are positive integers and 1≤i≤K.

公开(公告)号：US20190138838A1

公开(公告)日：2019-05-09

申请号：US15936755

申请日：2018-03-27

Applicant: BOE Technology Group Co., Ltd.

Inventor： Hanwen Liu ,  Pablo Navarrete Michelini

IPC: G06K9/40 ,  G06N3/02 ,  G06T5/00

Abstract: There are provided an image processing method and an image processing device. The image processing method comprises: acquiring an input image; acquiring a first noise image and a second noise image; executing image conversion processing on the input image with the first noise image using a generative neural network, to acquire a first output image; and executing high resolution conversion processing on the first output image with the second noise image using a super-resolution neural network, to acquire a second output image, wherein the first noise image is different from the second noise image.

公开(公告)号：US20180211157A1

公开(公告)日：2018-07-26

申请号：US15712654

申请日：2017-09-22

Applicant: BOE Technology Group Co., Ltd.

Inventor： Hanwen Liu ,  Pablo Navarrete Michelini

IPC: G06N3/04 ,  G06T3/40 ,  G06K9/46

CPC classification number: G06N3/0454 ,  G06K9/46 ,  G06K9/6232 ,  G06T3/4007 ,  G06T3/4046

Abstract: An image processing method and an image processing device are provided. The image processing method includes steps of extracting a feature of an inputted first image by a first CNN, and reconstructing and outputting an image by a second CNN. The first CNN includes a plurality of first convolutional layers connected sequentially to each other and a plurality of first pooling layers each arranged between respective adjacent first convolutional layers, and each first convolutional layer is configured to generate and output a first convolutional feature. The second CNN includes a plurality of second convolutional layers connected sequentially to each other and a plurality of composite layers each arranged between respective adjacent second convolutional layers, and each composite layer is an up-sampling layer.

公开(公告)号：US12277686B2

公开(公告)日：2025-04-15

申请号：US17774610

申请日：2021-05-14

Applicant: BOE Technology Group Co., Ltd.

Inventor： Hanwen Liu ,  Tingting Wang ,  Guannan Chen

IPC: G06T5/70

Abstract: Provided is a method for processing an image. The method includes: acquiring a first original image to be processed; and acquiring a degraded image by performing down-sampling processing and blurring processing on the first original image according to a configured down-sampling processing algorithm and a blurring parameter; wherein the down-sampling processing algorithm includes a plurality of sampling steps.

公开(公告)号：US12198226B2

公开(公告)日：2025-01-14

申请号：US17907012

申请日：2021-12-28

Applicant: BOE Technology Group Co., Ltd.

Inventor： Dan Zhu ,  Guannan Chen ,  Hanwen Liu

IPC: G06T11/00 ,  G06T5/20 ,  G06T7/73 ,  G06V10/75 ,  G06V10/77 ,  G06V10/776 ,  G06V10/82

Abstract: A computer-implemented method is provided. The computer-implemented method includes inputting a low-resolution image and a plurality of high-resolution images into a feature extractor, the low-resolution image and the plurality of high-resolution images including images of a target object; obtaining, by the feature extractor, feature maps of the low-resolution image and the plurality of high-resolution images; comparing similarities between the feature maps of the low-resolution image and the plurality of high-resolution images; obtaining selected feature maps of one or more selected high-resolution images of the plurality of high-resolution images most similar to the low-resolution image; inputting the selected feature maps into a generator to output a repair image; enhancing the low-resolution image using a pre-processing image enhancing process to generate an enhanced image; and morphing the repair image with the enhanced image.

公开(公告)号：US12175628B2

公开(公告)日：2024-12-24

申请号：US17631481

申请日：2021-04-09

Applicant: BOE Technology Group Co., Ltd.

Inventor： Hanwen Liu

IPC: G06V40/18 ,  G06T3/4053 ,  G06T3/4076 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82

Abstract: Provided are a training method and apparatus for an image processing image processing model, and an image processing method and apparatus. The training method comprises: acquiring a sample image and a first reference image, wherein the information quantity and resolution of the sample image are respectively lower than those of the first reference image; inputting the sample image into a generative network in an image processing model, and carrying out super-resolution processing and down-sampling processing on the sample image by means of the generative network, so as to generate and output at least one result image; determining the total image loss of the at least one result image according to the first reference image; and adjusting parameters of the generative network according to the total image loss, so that the total image loss of at least one result image output by the adjusted generative network meets an image loss condition.

公开(公告)号：US11842267B2

公开(公告)日：2023-12-12

申请号：US16492873

申请日：2019-03-22

Applicant: BOE Technology Group Co., Ltd.

Inventor： Hanwen Liu ,  Pablo Navarrete Michelini ,  Lijie Zhang ,  Dan Zhu

IPC: G06N3/08 ,  G06T3/40 ,  G06F18/211 ,  G06F18/213

CPC classification number: G06N3/08 ,  G06F18/211 ,  G06F18/213 ,  G06T3/4007 ,  G06T3/4046

Abstract: A computer-implemented method using a convolutional neural network is provided. The computer-implemented method using a convolutional neural network includes processing an input image through at least one channel of the convolutional neural network to generate an output image including content features of the input image morphed with style features of a reference style image. The at least one channel includes a down-sampling segment, a densely connected segment, and an up-sampling segment sequentially connected together. Processing the input image through the at least one channel of the convolutional neural network includes processing an input signal through the down-sampling segment to generate a down-sampling segment output; processing the down-sampling segment output through the densely connected segment to generate a densely connected segment output; and processing the densely connected segment output through the up-sampling segment to generate an up-sampling segment output. The input signal includes a component of the input image.

公开(公告)号：US11763762B2

公开(公告)日：2023-09-19

申请号：US17417468

申请日：2020-12-30

Applicant: BOE Technology Group Co., Ltd.

Inventor： Hanwen Liu ,  Yanhong Wu ,  Lijie Zhang

IPC: G09G3/34

CPC classification number: G09G3/344 ,  G09G2340/06

Abstract: The present disclosure provides an image processing method, an image processing device, and a display device. The image processing method includes: acquiring image data including display data of all of pixels of an image; and performing, on the display data of each of the pixels, operations of: determining Euclidean distances from the display data of the pixel to the display data of a first pure color, the display data of a second pure color, and the display data of a third pure color in a set color space; and replacing the display data of the pixel with one of the display data of the first pure color, the display data of the second pure color and the display data of the third pure color according to the determined Euclidean distances and a preset rule.