Tencent Technology (shenzhen) Company Limited

Junhong Huang

Jing Liu

Yi Liu

Yongjian Wu

Yuwing Tai

Qiang Fu

Minghui Wang

Huixing Wang

Shang Yu

Zhihao Wang

Da Yao

Yin Lu

Jiancheng Lin

Lizhao Gao

Fangmin Chen

Hengfeng Tian

Yubin Xie

Liuji Zhou

Haiyou Li

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.

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

Embodiments of the present invention provide a video processing method, a mobile terminal, and a server. The method may include: sending, by a mobile terminal, a request to a server for pulling status update data of a social network, so that the server acquires original status update data that is requested to be pulled, the original status update data including a source video address; performing, by the server, adaptation processing on the source video address, to generate an adaptive video address; updating, by the server, the original status update data by using the adaptive video address, to obtain optimized status update data, and returning the optimized status update data to the mobile terminal; and obtaining, by the mobile terminal, adaptive video data according to the adaptive video address in the optimized status update data, and playing the adaptive video data.

Video processing method, mobile terminal, and server

Growing community of inventors

Shenzhen, China

Junhong Huang