Related papers: Enhancing Frequency for Single Image Super-Resolut…
Dense self-supervised learning (SSL) methods showed its effectiveness in enhancing the fine-grained semantic understandings of vision models. However, existing approaches often rely on parametric assumptions or complex post-processing…
The single image super-resolution task is one of the most examined inverse problems in the past decade. In the recent years, Deep Neural Networks (DNNs) have shown superior performance over alternative methods when the acquisition process…
It is widely agreed that reference-based super-resolution (RefSR) achieves superior results by referring to similar high quality images, compared to single image super-resolution (SISR). Intuitively, the more references, the better…
Kernel Regularized Least Squares (KRLS) is a popular method for flexibly estimating models that may have complex relationships between variables. However, its usefulness to many researchers is limited for two reasons. First, existing…
This paper describes a fast and accurate method for obtaining steerable principal components from a large dataset of images, assuming the images are well localized in space and frequency. The obtained steerable principal components are…
A multilevel kernel-based interpolation method, suitable for moderately high-dimensional function interpolation problems, is proposed. The method, termed multilevel sparse kernel-based interpolation (MLSKI, for short), uses both level-wise…
Deep learning (DL) architectures for superresolution (SR) normally contain tremendous parameters, which has been regarded as the crucial advantage for obtaining satisfying performance. However, with the widespread use of mobile phones for…
Even without auxiliary images, single hyperspectral image super-resolution (SHSR) methods can be designed to improve the spatial resolution of hyperspectral images. However, failing to explore coherence thoroughly along bands and…
With the inspiration of vision transformers, the concept of depth-wise convolution revisits to provide a large Effective Receptive Field (ERF) using Large Kernel (LK) sizes for medical image segmentation. However, the segmentation…
Recent works on single-image super-resolution are concentrated on improving performance through enhancing spatial encoding between convolutional layers. In this paper, we focus on modeling the correlations between channels of convolutional…
Large language models (LLMs) have demonstrated remarkable capabilities, yet prohibitive parameter complexity often hinders their deployment. Existing singular value decomposition (SVD) based compression methods simply deem singular values…
For lossy image compression systems, we develop an algorithm, iterative refinement, to improve the decoder's reconstruction compared to standard decoding techniques. Specifically, we propose a recurrent neural network approach for…
We propose a novel sparsity enhancement strategy for regression tasks, based on learning a data-adaptive kernel metric, i.e., a shape matrix, through 2-Layered kernel machines. The resulting shape matrix, which defines a Mahalanobis-type…
Recent improvements in convolutional neural network (CNN)-based single image super-resolution (SISR) methods rely heavily on fabricating network architectures, rather than finding a suitable training algorithm other than simply minimizing…
In the last few decades, significant achievements have been attained in predicting where humans look at images through different computational models. However, how to determine contributions of different visual features to overall saliency…
Existing data augmentation in self-supervised learning, while diverse, fails to preserve the inherent structure of natural images. This results in distorted augmented samples with compromised semantic information, ultimately impacting…
This work presents a lightweight super-resolution (LiteSR) neural network for depth and intensity images acquired from a consumer-grade single-photon avalanche diode (SPAD) array with a 48x32 spatial resolution. The proposed framework…
Deep learning has been used to image compressive sensing (CS) for enhanced reconstruction performance. However, most existing deep learning methods train different models for different subsampling ratios, which brings additional hardware…
Low-light image enhancement (LLIE) aims to improve the illuminance of images due to insufficient light exposure. Recently, various lightweight learning-based LLIE methods have been proposed to handle the challenges of unfavorable prevailing…
While burst Low-Resolution (LR) images are useful for improving their Super Resolution (SR) image compared to a single LR image, prior burst SR methods are trained in a deterministic manner, which produces a blurry SR image. Since such…