Super-resolution (SR) is a technique that produces a high resolution (HR) image via employing a number of low resolution (LR) images from the same scene. One of the degradations that attenuates performance of the SR is the blurriness of the input LR images. In many previous works in the SR, the blurriness of the LR images is assumed to be due to the integral effect of the image sensor of the im...

Super-resolution is a process that combines information from some low-resolution images in order to produce an image with higher resolution. In most of the previous related work, the blurriness that is associated with low resolution images is assumed to be due to the integral effect of the acquisition device’s image sensor. However, in practice there are other sources of blurriness as well, inc...

Blind image deblurring, i.e., deblurring without knowledge of the blur kernel, is a highly ill-posed problem. The problem can be solved in two parts: i) estimate a blur kernel from the blurry image, and ii) given estimated blur kernel, de-convolve blurry input to restore the target image. In this paper, by interpreting an image patch as a signal on a weighted graph, we first argue that a skelet...

Most existing non-blind image deblurring methods assume that the blur kernel is free of error. However, it is often unavoidable in practice that the input blur kernel is erroneous to some extent. Sometimes the error could be severe, e.g, for images degraded by non-uniform motion blurring. When an inaccurate blur kernel is used as the input, significant distortions will appear in the image recov...

Image motion deblurring with unknown blur kernel is an ill-posed problem. This paper proposes a blind motion deblurring approach that solves blur kernel and the latent image robustly. For kernel optimization, an edge mask is used as an image prior to improve kernel update, then an edge selection mask is adopted to improve image update. In addition, an alternative iterative method is introduced ...

One of the long-standing challenges in photography is motion blur. Blur artifacts are generated from relative motion between a camera and a scene during exposure. While blur can be reduced by using a shorter exposure, this comes at an unavoidable trade-off with increased noise. Therefore, it is desirable to remove blur computationally. To remove blur, we need to (i) estimate how the image is bl...

We provide additional quantitative and qualitative comparisons on two more publicly available datasets, Köhler et al. [2] and Lai et al. [3] respectively, in this supplementary material to demonstrate the efficacy of our proposed network. We also provide an analysis on the deblurring efficiency and generalizability of our network when compared to a network learned for a single blur kernel. Alon...

The aim of this article is to propose a blur kernel estimation method based on the new concept of the Multiplicative Multiresolution Decomposition (MMD). This method quantifies the blur effect in the MMD’s domain by analyzing edges spreading through a multiresolution analysis. The histogram of edges spreading over the entire image is used as information about the blur amount in the image. Tests...