Related papers: Multi-scale and Multi-directional VLBI Imaging wit…
Despite the impressive advancements of Large Vision-Language Models (LVLMs), existing approaches suffer from a fundamental bottleneck: inefficient visual-language integration. Current methods either disrupt the model's inherent structure or…
Deep neural networks are playing an important role in state-of-the-art visual recognition. To represent high-level visual concepts, modern networks are equipped with large convolutional layers, which use a large number of filters and…
Space Very-Long-Baseline-Interferometry (S-VLBI) observations at high frequencies hold the prospect of achieving the highest angular resolutions and astrometric accuracies, resulting from the long baselines between ground and satellite…
The recent development of $\theta\mhyphen\theta$ techniques in pulsar scintillometry has opened the door for new high resolution imaging techniques of the scattering medium. By solving the phase retrieval problem and recovering the…
Retinal fundus images provide valuable insights into the human eye's interior structure and crucial features, such as blood vessels, optic disk, macula, and fovea. However, accurate segmentation of retinal blood vessels can be challenging…
We present the results of the pilot observations of the Deep Extragalactic VLBI-Optical Survey (DEVOS). Our ultimate aim is to collect information on compact structures in a large sample of extragalactic radio sources (~10000 objects) up to…
T2-weighted magnetic resonance imaging (MRI) and diffusion-weighted imaging (DWI) are essential components for cervical cancer diagnosis. However, combining these channels for training deep learning models are challenging due to…
Background and Aim: Over-fitting issue has been the reason behind deep learning technology not being successfully implemented in oral cancer images classification. The aims of this research were reducing overfitting for accurately producing…
Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this CVPR 2015 paper, we discover that a high-quality visual saliency model can be trained with multiscale features…
In this paper, we propose a novel design of image deblurring in the form of one-shot convolution filtering that can directly convolve with naturally blurred images for restoration. The problem of optical blurring is a common disadvantage to…
One of the fundamental challenges in supervised learning for multimodal image registration is the lack of ground-truth for voxel-level spatial correspondence. This work describes a method to infer voxel-level transformation from…
Image synthesis from corrupted contrasts increases the diversity of diagnostic information available for many neurological diseases. Recently the image-to-image translation has experienced significant levels of interest within medical…
Depth completion, which aims to generate high-quality dense depth maps from sparse depth maps, has attracted increasing attention in recent years. Previous work usually employs RGB images as guidance, and introduces iterative spatial…
The challenge of Multimodal Deformable Image Registration (MDIR) lies in the conversion and alignment of features between images of different modalities. Generative models (GMs) cannot retain the necessary information enough from the source…
Imaging algorithms form powerful analysis tools for VLBI data analysis. However, these tools cannot measure certain image features (e.g., ring diameter) by their non-parametric nature. This is unfortunate since these image features are…
This paper introduces the Wide-band Asp-Clean (\texttt{WAsp}) algorithm, a novel scale-sensitive image reconstruction method tailored for wide-band imaging applications. This algorithm is particularly beneficial for thermal noise-limited…
Centaurus A is the closest active galactic nucleus. High resolution imaging using Very Long Baseline Interferometry (VLBI) enables us to study the spectral and kinematic behavior of the radio jet-counterjet system on sub-parsec scales,…
The reconstruction of the polarization of a source in radio interferometry is a challenging calibration problem since the reconstruction strongly depends on the gains and leakages that need to be inferred along with the image. This is…
High-resolution (HR) magnetic resonance imaging (MRI) is crucial for many clinical and research applications. However, achieving it remains costly and constrained by technical trade-offs and experimental limitations. Super-resolution (SR)…
Data sizes for next generation radio telescopes, such as the Square Kilometre Array (SKA), are far above that of their predecessors. The CLEAN algorithm was originally developed by H\"ogbom [1974], long before such data sizes were thought…