Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020108336 - IMAGE PROCESSING METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM

Publication Number WO/2020/108336
Publication Date 04.06.2020
International Application No. PCT/CN2019/119087
International Filing Date 18.11.2019
IPC
H04N 21/234 2011.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
21Selective content distribution, e.g. interactive television or video on demand
20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
23Processing of content or additional data; Elementary server operations; Server middleware
234Processing of video elementary streams, e.g. splicing of video streams or manipulating MPEG-4 scene graphs
CPC
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
H04N 21/234
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
21Selective content distribution, e.g. interactive television or video on demand [VOD]
20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
23Processing of content or additional data; Elementary server operations; Server middleware
234Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
H04N 21/4402
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
21Selective content distribution, e.g. interactive television or video on demand [VOD]
40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
43Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network, synchronizing decoder's clock; Client middleware
44Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
4402involving reformatting operations of video signals for household redistribution, storage or real-time display
Applicants
  • 腾讯科技(深圳)有限公司 TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED [CN]/[CN]
Inventors
  • 揭泽群 JIE, Zequn
Agents
  • 广州华进联合专利商标代理有限公司 ADVANCE CHINA IP LAW OFFICE
Priority Data
201811457745.530.11.2018CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) IMAGE PROCESSING METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM
(FR) PROCÉDÉ ET APPAREIL DE TRAITEMENT D'IMAGE, DISPOSITIF ET SUPPORT D'ENREGISTREMENT
(ZH) 图像处理方法、装置、设备及存储介质
Abstract
(EN)
Disclosed in the embodiments of the present application are an image processing method and apparatus, a device, and a storage medium. The method comprises: inputting an original image into a decoding network according to an image conversion instruction, and outputting a first feature map of the original image; inputting the first feature map sequentially into a plurality of conversion networks corresponding to at least one piece of conversion requirement information, and outputting a second feature map; and inputting the second feature map into a reconstruction network, and outputting a target image.
(FR)
Selon divers modes de réalisation, la présente invention concerne un procédé et un appareil de traitement d'image, un dispositif et un support d'enregistrement. Le procédé comprend les étapes consistant à : entrer une image d'origine dans un réseau de décodage selon une instruction de conversion d'image, et délivrer en sortie une première carte de caractéristiques de l'image d'origine; entrer la première carte de caractéristiques séquentiellement dans une pluralité de réseaux de conversion correspondant à au moins un élément d'informations d'exigence de conversion, et délivrer en sortie une seconde carte de caractéristiques; et entrer la seconde carte de caractéristiques dans un réseau de reconstruction, et délivrer en sortie une image cible.
(ZH)
本申请实施例公开了一种图像处理方法、装置、设备及存储介质。所述方法包括:根据图像变换指令,将原始图像输入解码网络,输出该原始图像的第一特征图;将该第一特征图依次输入与至少一个变换需求信息对应的多个变换网络,输出第二特征图;将该第二特征图输入重建网络,输出目标图像。
Also published as
Latest bibliographic data on file with the International Bureau