期刊
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
卷 -, 期 -, 页码 2480-2485出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPRW53098.2021.00281
关键词
-
This study introduces an Efficient Video Super-Resolution Network (EVSRNet) with neural architecture search for real-time video super-resolution, demonstrating a good balance between quality and efficiency. The method achieved competitive results in the Mobile AI 2021 real-time video super-resolution challenge, being the fastest and significantly outperforming other competitors.
With the development of convolutional neural networks (CNN), the super-resolution results of CNN-based method have far surpassed traditional method. In particular, the CNN-based single image super-resolution method has achieved excellent results. Video sequences contain more abundant information compare with image, but there are few video super-resolution methods that can be applied to mobile devices due to the requirement of heavy computation, which limits the application of video super-resolution. In this work, we propose the Efficient Video Super-Resolution Network (EVSRNet) with neural architecture search for real-time video super-resolution. Extensive experiments show that our method achieves a good balance between quality and efficiency. Finally, we achieve a competitive result of 7.36 where the PSNR is 27.85 dB and the inference time is 11.3 ms/f on the target snapdragon 865 SoC, resulting in a 2nd place in the Mobile AI(MAI) 2021 real-time video super-resolution challenge. It is noteworthy that, our method is the fastest and significantly outperforms other competitors by large margins.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据