The Hong Kong University of Science and Technology

China Petroleum Chemical Corporation

Sinopec Research Institute of Safety Engineering Co., Ltd.

Song Wen

Zhe Yang

Shueng Han Gary Chan

Feng Sun

Bing Sun

Shoutao Ma

Wei Xu

Lei Zhao

Yuxia Zhang

Changsheng Zhang

Yunfeng Zhu

A VSR approach with temporal consistency using generative adversarial networks (VistGAN) that requires only the training HR video sequence to generate the HR/LR video frame pairs, instead of the pre-artificial-synthesized HR/LR video frame pairs, for training. By this unsupervised learning method, the encoder degrades the input HR video frames of a training HR video sequence to their LR counterparts, and the decoder seeks to recover the original HR video frames from the LR video frames. To improve the temporal consistency the unsupervised learning method provides a sliding window that explores the temporal correlation in both HR and LR domains. It keeps the temporal consistent and also fully utilizes high-frequency details from the last-generated reconstructed HR video frame.

VistGAN: unsupervised video super-resolution with temporal consistency using GAN

Growing community of inventors

Hong Kong, China

Song Wen