Advanced Super-Resolution using Lossless Pooling Convolutional Networks

2019 IEEE Winter Conference on Applications of Computer Vision (WACV)(2018)

引用 3|浏览6
暂无评分
摘要
In this paper, we present a novel deep learning-based approach for still image super-resolution, that unlike the mainstream models does not rely solely on the input low resolution image for high quality upsampling, and takes advantage of a set of artificially created auxiliary self-replicas of the input image that are incorporated in the neural network to create an enhanced and accurate upscaling scheme. Inclusion of the proposed lossless pooling layers, and the fusion of the input self-replicas enable the model to exploit the high correlation between multiple instances of the same content, and eventually result in significant improvements in the quality of the super-resolution, which is confirmed by extensive evaluations.
更多
查看译文
关键词
lossless pooling convolutional networks,deep learning-based approach,artificially created auxiliary self-replicas,neural network,lossless pooling layers,upscaling scheme,still image superresolution,input self-replicas fusion
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要