Related papers: A Frequency Domain Neural Network for Fast Image S…
Many existing interpretation methods of convolutional neural networks (CNNs) mainly analyze in spatial domain, yet model interpretability in frequency domain has been rarely studied. To the best of our knowledge, there is no study on the…
Due to the limitations of hyperspectral imaging systems, hyperspectral imagery (HSI) often suffers from poor spatial resolution, thus hampering many applications of the imagery. Hyperspectral super-resolution refers to fusing HSI and MSI to…
The Reference-based Super-resolution (RefSR) super-resolves a low-resolution (LR) image given an external high-resolution (HR) reference image, where the reference image and LR image share similar viewpoint but with significant resolution…
The convolution potential arises in a wide variety of application areas, and its efficient and accurate evaluation encounters three challenges: singularity, nonlocality and anisotropy. We introduce a fast algorithm based on a far-field…
Magnetic resonance image reconstruction starting from undersampled k-space data requires the recovery of many potential nonlinear features, which is very difficult for algorithms to recover these features. In recent years, the development…
The search for efficient neural network architectures has gained much focus in recent years, where modern architectures focus not only on accuracy but also on inference time and model size. Here, we present FUN, a family of novel…
In this paper, we introduce deep learning technology to tackle two traditional low-level image processing problems, companding and inverse halftoning. We make two main contributions. First, to the best knowledge of the authors, this is the…
In this paper, based on neural networks, we develop a data-driven model for extremely fast prediction of steady-state heat convection of a hot object with arbitrary complex geometry in a two-dimensional space. According to the governing…
Previous research has shown that computation of convolution in the frequency domain provides a significant speedup versus traditional convolution network implementations. However, this performance increase comes at the expense of repeatedly…
Deep convolutional neural networks (DCNNs) have recently demonstrated high-quality results in single-image super-resolution (SR). DCNNs often suffer from over-parametrization and large amounts of redundancy, which results in inefficient…
Conventional Fourier-domain Optical Coherence Tomography (FD-OCT) systems depend on resampling into wavenumber (k) domain to extract the depth profile. This either necessitates additional hardware resources or amplifies the existing…
In this paper we propose a conceptual framework for higher-order artificial neural networks. The idea of higher-order networks arises naturally when a model is required to learn some group of transformations, every element of which is…
This paper explores convolutional generative networks as an alternative to iterative reconstruction algorithms in medical image reconstruction. The task of medical image reconstruction involves mapping of projection main data collected from…
Recent learning-based lossless image compression methods encode an image in the unit of subimages and achieve comparable performances to conventional non-learning algorithms. However, these methods do not consider the performance drop in…
One impressive advantage of convolutional neural networks (CNNs) is their ability to automatically learn feature representation from raw pixels, eliminating the need for hand-designed procedures. However, recent methods for single image…
Inverse problems in image reconstruction are fundamentally complicated by unknown noise properties. Classical iterative deconvolution approaches amplify noise and require careful parameter selection for an optimal trade-off between…
Recent deep-learning based Super-Resolution (SR) methods have achieved remarkable performance on images with known degradation. However, these methods always fail in real-world scene, since the Low-Resolution (LR) images after the ideal…
Recently, deep learning based video super-resolution (SR) methods have achieved promising performance. To simultaneously exploit the spatial and temporal information of videos, employing 3-dimensional (3D) convolutions is a natural…
In recent years, sub-grid models for turbulent mixing have been developed by data-driven methods for large eddy simulation (LES). Super-resolution is a data-driven deconvolution technique in which deep convolutional neural networks are…
This chapter provides an overview of deep learning techniques for improving the spatial resolution of MRI, ranging from convolutional neural networks, generative adversarial networks, to more advanced models including transformers,…