- Patent Title: Computer-implemented method using a neural network comprising down-sampling segment, densely connected segment, and up-sampling segment, apparatus, and computer-program product
-
Application No.: US16492873Application Date: 2019-03-22
-
Publication No.: US11842267B2Publication Date: 2023-12-12
- Inventor: Hanwen Liu , Pablo Navarrete Michelini , Lijie Zhang , Dan Zhu
- Applicant: BOE Technology Group Co., Ltd.
- Applicant Address: CN Beijing
- Assignee: BOE Technology Group Co., Ltd.
- Current Assignee: BOE Technology Group Co., Ltd.
- Current Assignee Address: CN Beijing
- Agency: Intellectual Valley Law, P.C.
- Priority: CN 1811123875.5 2018.09.26
- International Application: PCT/CN2019/079242 2019.03.22
- International Announcement: WO2020/062809A 2020.04.02
- Date entered country: 2019-09-10
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06T3/40 ; G06F18/211 ; G06F18/213

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.
Public/Granted literature
- US20210326691A1 COMPUTER-IMPLEMENTED METHOD, APPARATUS, AND COMPUTER-PROGRAM PRODUCT Public/Granted day:2021-10-21
Information query