1. Introduction
Image alignment is one of the most widely used image processing techniques in computer vision [24]. The technique seeks the optimal image transformations to establish spatial correspondences between different image acquisitions. Applications in video stabilization [19], medical image registration [23], image recognition [27] and visual tracking [31] all leverage alignment to estimate image correspondences. In recent years, with the increasing popularity of the image and video sharing in social networks, such as Facebook and Instagram, we are seeing a dramatic increasing amount of visual data available online. Such enormous data poses great challenges for existing batch image alignment algorithms, due to great illumination variations between images, partial occlusion, gross pixel corruption, and the dynamically increasing images [2]. Therefore, the robust alignment with both memory and time efficiency deems to be a crucial image processing issue to be resolved for handling large and increasing amount of images.