General image super-resolution techniques have difficulties in recovering detailed face structures when applying to low resolution images. Recent deep learning based methods tailored for images achieved improved performance by jointly trained with additional task such as parsing and landmark prediction. However, multi-task requires extra manually labeled data. Besides, most of the existing work...

Spatial and channel attentions, modelling the semantic interdependencies in spatial dimensions respectively, have recently been widely used for segmentation. However, computing attentions separately sometimes causes errors, especially those difficult cases. In this paper, we propose Channelized Axial Attention (CAA) to seamlessly integrate attention into a single operation with negligible compu...