Ph.D. student Gunnam Suryanarayana's paper "Infrared super-resolution imaging using multi-scale saliency and deep wavelet residuals" (by Gunnam Suryanarayana , Enmei Tu, Jie Yang) has been accepted by Infrared Phyics and Technology.

        This paper proposes a new SR technique based on the multi-scale saliency detection and the residuals learned by the deep convolutional neural network in the wavelet domain. It decomposes an image into its low-frequency and high-frequency subbands. The multi-scale saliency detection is used to extract small scale and large scale salient feature maps from the bicubic upscaled LR image. These maps are incorporated in the highfrequency subbands of the LR image. The proposed method requires less computational time.