Results 51 to 60 of about 557,712 (297)
A motion parameters estimating method based on deep learning for visual blurred object tracking
IET Image Processing, 2021 Tracking the specific object in the blurred scenes is one of the challenging problems in computer vision and image processing. The accuracy and performance of trackers within the blur frames usually demonstrate a severe decrease.
Iman Iraei, Karim Faez
doaj +1 more source
Mathematical Problems of Computer Science, 2021 In this paper, we present deep learning-based blind image deblurring methods for estimating and removing a non-uniform motion blur from a single blurry image. We propose two fully convolutional neural networks (CNN) for solving the problem.
Misak T. Shoyan +2 more
doaj +1 more source
Understanding Kernel Size in Blind Deconvolution
, 2019 Most blind deconvolution methods usually pre-define a large kernel size to guarantee the support domain. Blur kernel estimation error is likely to be introduced, yielding severe artifacts in deblurring results.
Ren, Dongwei, Si-Yao, Li, Yin, Qian
core +1 more source
Gram filtering and sinogram interpolation for pixel-basis in parallel-beam X-ray CT reconstruction
, 2020 The key aspect of parallel-beam X-ray CT is forward and back projection, but its computational burden continues to be an obstacle for applications.
Entezari, Alireza, Shu, Ziyu
core +1 more source
Unsupervised Blur Kernel Estimation and Correction for Blind Super-Resolution
IEEE Access, 2022 Blind super-resolution (blind-SR) is an important task in the field of computer vision and has various applications in real-world. Blur kernel estimation is the main element of blind-SR along with the adaptive SR networks and a more accurately estimated ...
Youngsoo Kim +3 more
doaj +1 more source
Fast and easy blind deblurring using an inverse filter and PROBE
, 2017 PROBE (Progressive Removal of Blur Residual) is a recursive framework for blind deblurring. Using the elementary modified inverse filter at its core, PROBE's experimental performance meets or exceeds the state of the art, both visually and quantitatively.
J Kotera +11 more
core +1 more source
Mathematical Degradation Model Learning for Terahertz Image Super-Resolution
IEEE Access, 2021 This study proposes a super-resolution (SR) method for terahertz time-domain spectroscopy (THz-TDS) images, combining a convolutional neural network (CNN) and a mathematical degradation model.
Yao Lu, Qi Mao, Jingbo Liu
doaj +1 more source
Joint Blind Motion Deblurring and Depth Estimation of Light Field
, 2018 Removing camera motion blur from a single light field is a challenging task since it is highly ill-posed inverse problem. The problem becomes even worse when blur kernel varies spatially due to scene depth variation and high-order camera motion.
A Beck +12 more
core +1 more source
Deblurring by Realistic Blurring
, 2020 Existing deep learning methods for image deblurring typically train models using pairs of sharp images and their blurred counterparts. However, synthetically blurring images do not necessarily model the genuine blurring process in real-world scenarios ...
Li, Hongdong +6 more
core +1 more source
Advanced Materials, EarlyView.A fully flexible ion‐gel‐gated graphene‐channel transistor driven by a triboelectric nanogenerator enables self‐powered tactile sensing and synaptic learning. Mimicking spike‐rate‐dependent plasticity, the device exhibits frequency‐selective potentiation and depression, supporting rate‐coded neuromorphic computation even under flex.
Hanseong Cho +3 more
wiley +1 more source