Related papers: Fast Omni-Directional Image Super-Resolution: Adap…

High-resolution is a key trend in the development of synthetic aperture radar (SAR), which enables the capture of fine details and accurate representation of backscattering properties. However, traditional high-resolution SAR imaging…

Classic image scaling (e.g. bicubic) can be seen as one convolutional layer and a single upscaling filter. Its implementation is ubiquitous in all display devices and image processing software. In the last decade deep learning systems have…

The earlier works in the context of low-rank-sparse-decomposition (LRSD)-driven stationary synthetic aperture radar (SAR) imaging have shown significant improvement in the reconstruction-decomposition process. Neither of the proposed…

Diffusion models have significantly advanced the state of the art in image, audio, and video generation tasks. However, their applications in practical scenarios are hindered by slow inference speed. Drawing inspiration from the…

Rotating-view thick-slice acquisition is highly SNR-efficient for mesoscale diffusion MRI (dMRI) but requires numerous rotating views to satisfy Nyquist sampling, resulting in long scan time. We propose a self-supervised Spatial-Angular…

Digital aberration measurement and removal play a prominent role in computational imaging platforms aimed at achieving simple and compact optical arrangements. A recent important class of such platforms is Fourier ptychography, which is…

Finite element methods typically require a high resolution to satisfactorily approximate micro and even macro patterns of an underlying physical model. This issue can be circumvented by appropriate multiscale strategies that are able to…

Object-centric scene understanding is a fundamental challenge in computer vision. Existing approaches often rely on multi-stage pipelines that first apply pre-trained segmentors to extract individual objects, followed by per-object 3D…

Modeling 3D humans accurately and robustly from a single image is very challenging, and the key for such an ill-posed problem is the 3D representation of the human models. To overcome the limitations of regular 3D representations, we…

Detecting spliced images is one of the emerging challenges in computer vision. Unlike prior methods that focus on detecting low-level artifacts generated during the manipulation process, we use an image retrieval approach to tackle this…

In this paper, we introduce a novel implicit neural network for the task of single image super-resolution at arbitrary scale factors. To do this, we represent an image as a decoding function that maps locations in the image along with their…

Large-scale pre-trained diffusion models have been extensively adopted for real-world image Super-Resolution because of their powerful generative priors through textual guidance. However, when super-resolving high-resolution images with…

Recently, Convolutional Neural Networks (CNNs) have been successfully adopted to solve the ill-posed single image super-resolution (SISR) problem. A commonly used strategy to boost the performance of CNN-based SISR models is deploying very…

State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs). Although CNNs offer promising perspectives for 2D image compression, extending such models to omnidirectional images is not…

Despite its fruitful applications in remote sensing, image super-resolution is troublesome to train and deploy as it handles different resolution magnifications with separate models. Accordingly, we propose a highly-applicable…

The convolutional neural network model for optical flow estimation usually outputs a low-resolution(LR) optical flow field. To obtain the corresponding full image resolution,interpolation and variational approach are the most common…

Implicit neural representations (INRs) have significantly advanced the field of arbitrary-scale super-resolution (ASSR) of images. Most existing INR-based ASSR networks first extract features from the given low-resolution image using an…

To render a spherical (360 degree or omnidirectional) image on planar displays, a 2D image -- called as viewport -- must be obtained by projecting a sphere region on a plane, according to the users viewing direction and a predefined field…

Achieving high-quality High Dynamic Range (HDR) imaging on resource-constrained edge devices is a critical challenge in computer vision, as its performance directly impacts downstream tasks such as intelligent surveillance and autonomous…

Learning-based deformable image registration (DIR) accelerates alignment by amortizing traditional optimization via neural networks. Label supervision further enhances accuracy, enabling efficient and precise nonlinear alignment of unseen…