Adapting Image Super-Resolution State-of-the-Arts and Learning Multi-Model Ensemble for Video Super-Resolution
Abstract
Recently, image super-resolution has been widely studied and achieved significant progress by leveraging the power of deep convolutional neural networks. However, there has been limited advancement in video super-resolution (VSR) due to the complex temporal patterns in videos. In this paper, we investigate how to adapt state-of-the-art methods of image super-resolution for video super-resolution. The proposed adapting method is straightforward. The information among successive frames is well exploited, while the overhead on the original image super-resolution method is negligible. Furthermore, we propose an learning-based method to ensemble the outputs from multiple super-resolution models. Our methods show superior performance and rank second in the NTIRE2019 Video Super-Resolution Challenge Track 1.
Cite
Text
Li et al. "Adapting Image Super-Resolution State-of-the-Arts and Learning Multi-Model Ensemble for Video Super-Resolution." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00255Markdown
[Li et al. "Adapting Image Super-Resolution State-of-the-Arts and Learning Multi-Model Ensemble for Video Super-Resolution." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/li2019cvprw-adapting/) doi:10.1109/CVPRW.2019.00255BibTeX
@inproceedings{li2019cvprw-adapting,
title = {{Adapting Image Super-Resolution State-of-the-Arts and Learning Multi-Model Ensemble for Video Super-Resolution}},
author = {Li, Chao and He, Dongliang and Liu, Xiao and Ding, Yukang and Wen, Shilei},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {2033-2040},
doi = {10.1109/CVPRW.2019.00255},
url = {https://mlanthology.org/cvprw/2019/li2019cvprw-adapting/}
}