Anchored Neighborhood Regression for Fast Example-Based Super-Resolution

Recently there have been significant advances in image up scaling or image super-resolution based on a dictionary of low and high resolution exemplars. The running time of the methods is often ignored despite the fact that it is a critical factor for real applications. This paper proposes fast super-resolution methods while making no compromise on quality. First, we support the use of sparse learned dictionaries in combination with neighbor embedding methods. In this case, the nearest neighbors are computed using the correlation with the dictionary atoms rather than the Euclidean distance. Moreover, we show that most of the current approaches reach top performance for the right parameters. Second, we show that using global collaborative coding has considerable speed advantages, reducing the super-resolution mapping to a precomputed projective matrix. Third, we propose the anchored neighborhood regression. That is to anchor the neighborhood embedding of a low resolution patch to the nearest atom in the dictionary and to precompute the corresponding embedding matrix. These proposals are contrasted with current state-of-the-art methods on standard images. We obtain similar or improved quality and one or two orders of magnitude speed improvements.

1. Introduction

Super-resolution (SR) is a popular branch of image reconstruction that focuses on the enhancement of image resolution. In general, it takes one or more low resolution (LR) images as input and maps them to a high resolution (HR) output image. Super-resolution algorithms can be roughly subdivided into three subclasses: interpolation methods like Lanczos upsampling [5] and New Edge Directed Interpolation (NEDI) [10], multi-frame methods [6], [7], [11] which make use of the presence of aliasing in multiple frames of the same scene to produce one high resolution image, and finally learning-based methods. The latter use machine learning techniques and comprise methods like Gradient Profile Prior [13], which try to learn edge statistics from natural images, but also the recent and very popular dictionary-or example-based learning methods. Most of these dictionary-based methods build on the work of Freeman et al. [8] and Baker and Kanade [2]. Figure 1. Speed vs. PSNR for the tested methods. Our ANR and GR methods (shown in red) provide both high speed and quality. More details in Table 1