Method for generating high-resolution picture, computer device, and storage medium

US11373275B2 · kind B2 · utility

Assignee

• TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED · CN

Inventors

• Yuwing Tai · Lo Wu, CN
• Lizhao Gao · Nanhu, CN
• Qiang Fu · Beijing, CN
• Fangmin CHEN · Nanhu, CN
• Da-Jeng Yao · Hsinchu, TW
• Hengfeng TIAN · Nanhu, CN
• Yubin Xie · New York, US
• Liuji Zhou · Nanhu, CN
• Tao Wang · Beijing, CN
• Yongjian Wu · Albany, US
• Junhong HUANG · Nanhu, CN

Key dates

• Filing date: Apr 29, 2020
• Grant date: Jun 28, 2022
• Expiry date: Jan 16, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/048
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

This application provides a method for generating a high-resolution picture performed by a computer device. The method includes: acquiring at least one deep neural network model; acquiring a low-resolution picture; determining a corresponding deep neural network model according to the low-resolution picture; and converting the low-resolution pictures into a high-resolution picture through the deep neural network model, the deep neural network model including a plurality of non-linear conversion convolution layers that alternately use different parameter matrices as convolution template parameters.