Bi-directional Projection Framework for Fast Single Image Super Resolution

Abstract

Background:: Collaborative Representation (CR) has been widely used in Single Image Super Resolution (SISR) with the assumption that Low-resolution (LR) and high-resolution (HR) features can be linearly represented by neighborhoods and share consistent CR coefficients. Numerous patents and journal papers have been published. However, this CR consistency does not hold in the reconstruction phase, which leads to degraded performance. Methods:: To fulfill this gap, we propose a novel bi-directional projection model (BDPM) to establish a bi-directional mapping between LR and HR features without any consistency constraint. The multiple projection matrices are offline computed to reduce reconstruction time greatly. We further develop several strategies to extract features and group neighborhoods such that local structures can be preserved better. Results:: Compared to the learning-based methods, BDPM is about 2 to 10 times faster and compared to the reconstruction-based methods, it is about 500 to 2,000 times faster. Conclusion:: The empirical studies verify the effectiveness of BDPM and extensive experimental results demonstrate that BDPM achieves better SISR performance than many state-of-the-arts.