Local self similarity-based super-resolution for asymmetric dual-camera

Abstract

This paper presents a super-resolution (SR) method for the asymmetric dual-camera system. The proposed method restores the high-resolution (HR) image using the local self-similarity between two input images as wide- and tele-view images. The proposed method consists of three steps: i) registration and warping processes to reduce the disparity between the input images, ii) high-frequency patch extraction from the tele-view image, and iii) super-resolution reconstruction using local self-similarity property. Experimental results show that the proposed method can significantly restore the HR image than existing interpolation and SR methods.