Results 21 to 30 of about 36,154 (265)
Pixel-Level Kernel Estimation for Blind Super-Resolution
IEEE Access, 2021 Throughout the past several years, deep learning-based models have achieved success in super-resolution (SR). The majority of these works assume that low-resolution (LR) images are ‘uniformly’ degraded from their corresponding high ...
Jaihyun Lew, Euiyeon Kim, Jae-Pil Heo
doaj +1 more source
Modeling nonstationary lens blur using eigen blur kernels for restoration
Optics Express, 2020 Images acquired through a lens show nonstationary blur due to defocus and optical aberrations. This paper presents a method for accurately modeling nonstationary lens blur using eigen blur kernels obtained from samples of blur kernels through principal component analysis. Pixelwise variant nonstationary lens blur is expressed as a linear combination of
Moonsung Gwak, Seungjoon Yang
openaire +3 more sources
Convergence Analysis of MAP Based Blur Kernel Estimation [PDF]
2017 IEEE International Conference on Computer Vision (ICCV), 2017 One popular approach for blind deconvolution is to formulate a maximum a posteriori (MAP) problem with sparsity priors on the gradients of the latent image, and then alternatingly estimate the blur kernel and the latent image. While several successful MAP based methods have been proposed, there has been much controversy and confusion about their ...
Sunghyun Cho, Seungyong Lee 0001
openaire +2 more sources
Effective Alternating Direction Optimization Methods for Sparsity-Constrained Blind Image Deblurring
Sensors, 2017 Single-image blind deblurring for imaging sensors in the Internet of Things (IoT) is a challenging ill-conditioned inverse problem, which requires regularization techniques to stabilize the image restoration process.
Naixue Xiong +5 more
doaj +1 more source
IEEE Access, 2020 Blind image deblurring, composed of estimating blur kernel and non-blind deconvolution, is an extremely ill-posed problem. However, previous deblurring methods still cannot solve delta kernel or noise problem well and avoid ringing artifacts in restored ...
Hongtian Zhao +3 more
doaj +1 more source
IMAGE SHARPENING WITH BLUR MAP ESTIMATION USING CONVOLUTIONAL NEURAL NETWORK [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2019 We propose a method for choosing optimal values of the parameters of image sharpening algorithm for out-of-focus blur based on grid warping approach. The idea of the considered sharpening algorithm is to move pixels from the edge neighborhood towards the
A. Nasonov, A. Krylov, D. Lyukov
doaj +1 more source
Cascaded Degradation-Aware Blind Super-Resolution
Sensors, 2023 Image super-resolution (SR) usually synthesizes degraded low-resolution images with a predefined degradation model for training. Existing SR methods inevitably perform poorly when the true degradation does not follow the predefined degradation ...
Ding Zhang +3 more
doaj +1 more source
Understanding and evaluating blind deconvolution algorithms [PDF]
, 2009 Blind deconvolution is the recovery of a sharp version of a blurred image when the blur kernel is unknown. Recent algorithms have afforded dramatic progress, yet many aspects of the problem remain challenging and hard to understand.The goal of this paper
Durand, Fredo +3 more
core +1 more source
Reconstruction of noisy and blurred images using blur kernel
IOP Conference Series: Materials Science and Engineering, 2017 Blur is a common in so many digital images. Blur can be caused by motion of the camera and scene object. In this work we proposed a new method for deblurring images. This work uses sparse representation to identify the blur kernel. By analyzing the image coordinates Using coarse and fine, we fetch the kernel based image coordinates and according to ...
Vijayan Ellappan, Vishal Chopra
openaire +1 more source
An Improved Feedback Network Superresolution on Camera Lens Images for Blind Superresolution
Journal of Electrical and Computer Engineering, 2021 Most of the recent advances in image superresolution (SR) assume that the blur kernel during downsampling is predefined (e.g., Bicubic or Gaussian kernel), but it is a difficult task to make it suitable for all the realistic images.
Yuhao Liu
doaj +1 more source