Results 161 to 170 of about 750,933 (209)
Some of the next articles are maybe not open access.
Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution
IEEE International Conference on Computer Vision, 2023Although deep learning-based solutions have achieved impressive reconstruction performance in image super-resolution (SR), these models are generally large, with complex architectures, making them incompatible with low-power devices with many ...
Long Sun +3 more
semanticscholar +1 more source
Zernike-Moment-Based Image Super Resolution
IEEE Transactions on Image Processing, 2011Multiframe super-resolution (SR) reconstruction aims to produce a high-resolution (HR) image using a set of low-resolution (LR) images. In the process of reconstruction, fuzzy registration usually plays a critical role. It mainly focuses on the correlation between pixels of the candidate and the reference images to reconstruct each pixel by averaging ...
Gao, Xinbo +4 more
openaire +4 more sources
One-Step Effective Diffusion Network for Real-World Image Super-Resolution
Neural Information Processing SystemsThe pre-trained text-to-image diffusion models have been increasingly employed to tackle the real-world image super-resolution (Real-ISR) problem due to their powerful generative image priors.
Rongyuan Wu +3 more
semanticscholar +1 more source
Compressive image super-resolution
2009 Conference Record of the Forty-Third Asilomar Conference on Signals, Systems and Computers, 2009This paper proposes a new algorithm to generate a super-resolution image from a single, low-resolution input without the use of a training data set. We do this by exploiting the fact that the image is highly compressible in the wavelet domain and leverage recent results of compressed sensing (CS) theory to make an accurate estimate of the original high-
Pradeep Sen, Soheil Darabi
openaire +1 more source
Enhanced Deep Image Prior for Unsupervised Hyperspectral Image Super-Resolution
IEEE Transactions on Geoscience and Remote SensingDepending on a large-scale paired dataset of low-resolution hyperspectral image (LrHSI), high-resolution multispectral image (HrMSI), and corresponding high-resolution hyperspectral image (HrHSI), the supervised paradigm has achieved impressive ...
Jiaxin Li +5 more
semanticscholar +1 more source
Residual Feature Distillation Network for Lightweight Image Super-Resolution
ECCV Workshops, 2020Recent advances in single image super-resolution (SISR) explored the power of convolutional neural network (CNN) to achieve a better performance. Despite the great success of CNN-based methods, it is not easy to apply these methods to edge devices due to
Jie Liu, Jie Tang, Gangshan Wu
semanticscholar +1 more source
Super-resolution image reconstruction
2010 International Conference on Computer Application and System Modeling (ICCASM 2010), 2010Super-resolution image reconstruction is a technique to reconstruct high resolution image or video from a sequence of low resolution images. The super resolution method is summarized in this paper. The frequency domain method, non-uniform interpolation, POCS method, iterative back projection method, Bayesian approach, regularization method are both ...
null Xue-fen Wan, null Yi Yang
openaire +1 more source
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
TTST: A Top-k Token Selective Transformer for Remote Sensing Image Super-Resolution
IEEE Transactions on Image ProcessingTransformer-based method has demonstrated promising performance in image super-resolution tasks, due to its long-range and global aggregation capability. However, the existing Transformer brings two critical challenges for applying it in large-area earth
Yi Xiao +5 more
semanticscholar +1 more source
Model-Informed Multistage Unsupervised Network for Hyperspectral Image Super-Resolution
IEEE Transactions on Geoscience and Remote SensingBy fusing a low-resolution hyperspectral image (LrMSI) with an auxiliary high-resolution multispectral image (HrMSI), hyperspectral image super-resolution (HISR) can generate a high-resolution hyperspectral image (HrHSI) economically.
Jiaxin Li +5 more
semanticscholar +1 more source