Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CVPRW53098.2021.00281 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021) |
DocType | ISSN | Citations |
Conference | 2160-7508 | 0 |
PageRank | References | Authors |
0.34 | 0 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shaoli Liu | 1 | 0 | 0.68 |
Chengjian Zheng | 2 | 0 | 0.68 |
Kaidi Lu | 3 | 0 | 0.68 |
Gao Si | 4 | 0 | 0.68 |
Ning Wang | 5 | 0 | 0.68 |
Bofei Wang | 6 | 15 | 0.88 |
Diankai Zhang | 7 | 0 | 0.68 |
Xiaofeng Zhang | 8 | 0 | 0.68 |
Tianyu Xu | 9 | 0 | 0.34 |