Results 321 to 330 of about 10,359,966 (377)
Some of the next articles are maybe not open access.
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
ECCV Workshops, 2018The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts.
Xintao Wang +8 more
semanticscholar +1 more source
Color image resolution conversion
IEEE Transactions on Image Processing, 2005In this paper, we look at the problem of spatially scaling color images. We focus on an approach that takes advantage of the human visual system's color spatial frequency sensitivity. The algorithm performs an efficient least-squares (LS) resolution conversion for the luminance channel and a low-complexity pixel replication/reduction in the chrominance
openaire +2 more sources
Second-Order Attention Network for Single Image Super-Resolution
Computer Vision and Pattern Recognition, 2019Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and obtained remarkable performance.
Tao Dai +4 more
semanticscholar +1 more source
Gradient Image Super-resolution for Low-resolution Image Recognition
ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019In visual object recognition problems essential to surveillance and navigation problems in a variety of military and civilian use cases, low-resolution and low-quality images present great challenges to this problem. Recent advancements in deep learning based methods like EDSR/VDSR have boosted pixel domain image super-resolution (SR) performances ...
Dewan Fahim Noor +4 more
openaire +1 more source
Image Super-Resolution via Deep Recursive Residual Network
Computer Vision and Pattern Recognition, 2017Recently, Convolutional Neural Network (CNN) based models have achieved great success in Single Image Super-Resolution (SISR). Owing to the strength of deep networks, these CNN models learn an effective nonlinear mapping from the low-resolution input ...
Ying Tai, Jian Yang, Xiaoming Liu
semanticscholar +1 more source
Super-Resolution Image Restoration from Blurred Low-Resolution Images
Journal of Mathematical Imaging and Vision, 2005In this paper, we study the problem of reconstructing a high-resolution image from several blurred low-resolution image frames. The image frames consist of decimated, blurred and noisy versions of the high-resolution image. The high-resolution image is modeled as a Markov random field (MRF), and a maximum a posteriori (MAP) estimation technique is used
Michael K. Ng, Andy C. Yau
openaire +1 more source
Generation of high resolution images from low resolution images
NSIP 2005. Abstracts. IEEE-Eurasip Nonlinear Signal and Image Processing, 2005., 2005Summary form only given. It is known that some image enlarging methods work by extrapolating high-frequency components. The image enlarging method using the Bezier surface has been proposed, where it is assumed that each pixel has energy. The pixel energy is invariant during the enlarging process.
N. Kato, H. Yasukawa, A. Taguchi
openaire +1 more source
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
European Conference on Computer Vision, 2016We consider image transformation problems, where an input image is transformed into an output image. Recent methods for such problems typically train feed-forward convolutional neural networks using a per-pixel loss between the output and ground-truth ...
Justin Johnson +2 more
semanticscholar +1 more source
Isotope specific resolution recovery image reconstruction in high resolution PET imaging.
Medical physics, 2014Measuring and incorporating a scanner-specific point spread function (PSF) within image reconstruction has been shown to improve spatial resolution in PET. However, due to the short half-life of clinically used isotopes, other long-lived isotopes not used in clinical practice are used to perform the PSF measurements.
Kotasidis, Fotis +5 more
openaire +5 more sources
High-resolution image reconstruction from multiple low-resolution images
7th International Conference on Image Processing and its Applications, 1999In this paper, we demonstrate a digital signal processing (DSP) algorithm for improving spatial resolution of images captured by CMOS cameras. The basic approach is to reconstruct a high resolution (HR) image from a shift-related low resolution (LR) image sequence.
openaire +1 more source