Typical Super-resolution Algorithm Research Articles

KernelFlexSR: a self-adaptive super-resolution algorithm with multi-path convolution and residual network for dynamic kernel enhancement

Machine learning-based image super-resolution (SR) has garnered increasing research interest in recent years. However, there are two issues that have not been adequately addressed. The first issue is that existing SR methods often overlook the importance of improving the quality of the training dataset, which is a crucial factor in determining SR performance, regardless of the training method employed. The second issue is that while some studies report high numerical metrics, the visual results remain unsatisfactory. To address the first problem, we propose a new image down-sampling method to obtain higher-quality training datasets. To tackle the second problem, we present a new image super-resolution model based on a large-size convolution kernel and a multi-path algorithm. Specifically, we use an adaptive large-size convolutional kernel to extract features from the image based on the size of the input image, and a residual network to generate a deeper model to retain more details of the original input image. Experimental results demonstrate that the proposed multilayer downsampling method (MDM) can significantly improve the visual quality compared to traditional downsampling methods. Moreover, our proposed method achieves the best peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) values compared to several typical SR algorithms. Furthermore, subjective evaluation by human observers reveals that our method retains more details of the original image and produces smoother high-resolution images. Our proposed method effectively addresses the two aforementioned issues, which leads to improved SR performance in terms of both quantitative and qualitative measures.

Single image super-resolution via blind blurring estimation and dictionary learning

Learning-based methods have been becoming the mainstream of single image super resolution (SR) technologies. This kind of methods makes it effective to generate a high resolution (HR) image from a single low resolution (LR) image. There exists, however, two main problems with these methods: the quality of training data and the computational demand. We propose a novel framework for single image SR tasks in this paper, which consists of blur kernel estimation (BKE) and dictionary learning. BKE is utilized for improving the quality of training samples and realized by minimizing the dissimilarity between cross-scale patches iteratively. Couple dictionaries are trained by improved training samples before sparse recovery. More important is that a selective patch processing (SPP) strategy is adopted in BKE and sparse recovery, which brings more accurate BKE results and immensely reduces time consumption of the entire process. The experiments show that the proposed method produces more precise BKE estimation and better SR recovery than several typical SR algorithms at a higher efficiency.

Image Superresolution Based on Locally Adaptive Mixed‐Norm

In a typical superresolution algorithm, fusion error modeling, including registration error and additive noise, has a great influence on the performance of the super‐resolution algorithms. In this letter, we show that the quality of the reconstructed high‐resolution image can be increased by exploiting proper model for the fusion error. To properly model the fusion error, we propose to minimize a cost function that consists of locally and adaptively weighted L1‐ and L2‐norms considering the error model. Binary weights are used so as to adaptively select L1‐ or L2‐norm, based on the local errors. Simulation results demonstrate that proposed algorithm can overcome disadvantages of using either L1‐ or L2‐norm.