Results 41 to 50 of about 2,688,199 (290)
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
Unsupervised Degradation Representation Learning for Blind Super-Resolution [PDF]
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021 Most existing CNN-based super-resolution (SR) methods are developed based on an assumption that the degradation is fixed and known (e.g., bicubic downsampling). However, these methods suffer a severe performance drop when the real degradation is different from their assumption. To handle various unknown degradations in real-world applications, previous
Longguang Wang +6 more
openaire +3 more sources
Temporal Kernel Consistency for Blind Video Super-Resolution [PDF]
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021 Deep learning-based blind super-resolution (SR) methods have recently achieved unprecedented performance in upscaling frames with unknown degradation. These models are able to accurately estimate the unknown downscaling kernel from a given low-resolution (LR) image in order to leverage the kernel during restoration.
Lichuan Xiang +4 more
openaire +3 more sources
Blind Fusion of Hyperspectral Multispectral Images Based on Matrix Factorization
Remote Sensing, 2021 The fusion of low spatial resolution hyperspectral images and high spatial resolution multispectral images in the same scenario is important for the super-resolution of hyperspectral images.
Jian Long, Yuanxi Peng
doaj +1 more source
Scale Guided Hypernetwork for Blind Super-Resolution Image Quality Assessment [PDF]
, 2023 With the emergence of image super-resolution (SR) algorithm, how to blindly evaluate the quality of super-resolution images has become an urgent task.
Fu, Jun
core +1 more source
MoESR: Blind Super-Resolution using Kernel-Aware Mixture of Experts
, 2022 Modern deep learning super-resolution approaches have achieved remarkable performance where the low-resolution (LR) input is a degraded high-resolution (HR) image by a fixed known kernel i.e. kernel-specific super-resolution (SR).
Peemen, Maurice +5 more
core +1 more source
A Single-Frame Super-Resolution Innovative Approach
, 2007 Super-resolution refers to the process of obtaining a high resolution image from one or more low resolution images. In this work, we present a novel method for the super-resolution problem for the limited case, where only one image of low resolution is ...
Luz A. Torres-Méndez +5 more
core +1 more source
Self-FuseNet: Data Free Unsupervised Remote Sensing Image Super-Resolution
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023 Real-world degradations deviate from ideal degradations, as most deep learning-based scenarios involve the ideal synthesis of low-resolution (LR) counterpart images by popularly used bicubic interpolation. Moreover, supervised learning approaches rely on
Divya Mishra, Ofer Hadar
doaj +1 more source
Blind Super Resolution with Feature-Oriented Adaptive Degradation Adjustment
Tsinghua Science and TechnologyConventional methods in blind super-resolution first estimate the unknown degradation kernel from the low-resolution image and then leverage the degradation kernel for image reconstruction.
Hongxia Deng +6 more
doaj +1 more source
Boosting Degradation Representation Learning for Blind Image Super-Resolution [PDF]
Jisuanji kexue yu tansuoIn most convolutional neural networks-based super-resolution (SR) methods, the degradation assumptions are fixed and known (e.g., bicubic degradation). When applying them to real-world degraded images, the mismatch between the actual degradation and the ...
YUAN Jiang, MA Ji, ZHOU Dengwen
doaj +1 more source