Related papers: Ghost imaging based on Y-net: a dynamic coding and…

Deep convolutional networks (CNNs) have exhibited their potential in image inpainting for producing plausible results. However, in most existing methods, e.g., context encoder, the missing parts are predicted by propagating the surrounding…

Although supervised deep representation learning has attracted enormous attentions across areas of pattern recognition and computer vision, little progress has been made towards unsupervised deep representation learning for image…

The long time consumption is a bottleneck for the applicability of the ghost imaging (GI). By introducing a criterion for the convergence of GI, we investigate a factor that impacts on the convergence speed of it. Based on computer…

We proposed a novel approach to coherent imaging of dynamic samples. The inter-frame similarity of the sample's local structures is found to be a powerful constraint in phasing a sequence of diffraction patterns. We devised a new image…

Ghost imaging (GI) is a novel imaging technique based on the second-order correlation of light fields. Due to limited number of samplings in practice, traditional GI methods often reconstruct objects with unsatisfactory quality. To improve…

We propose a deep clustering architecture alongside image segmentation for medical image analysis. The main idea is based on unsupervised learning to cluster images on severity of the disease in the subject's sample, and this image is then…

Image composition is an important operation in image processing, but the inconsistency between foreground and background significantly degrades the quality of composite image. Image harmonization, aiming to make the foreground compatible…

For visual object recognition tasks, the illumination variations can cause distinct changes in object appearance and thus confuse the deep neural network based recognition models. Especially for some rare illumination conditions, collecting…

We propose a novel deep neural network architecture for the challenging problem of single image dehazing, which aims to recover the clear image from a degraded hazy image. Instead of relying on hand-crafted image priors or explicitly…

Computational ghost imaging needs to acquire a large number of correlated measurements between reference patterns and the scene for reconstruction, so extremely high acquisition speed is crucial for fast ghost imaging. With the development…

In surveillance, monitoring and tactical reconnaissance, gathering the right visual information from a dynamic environment and accurately processing such data are essential ingredients to making informed decisions which determines the…

In recent years, self-supervised denoising methods have gained significant success and become critically important in the field of image restoration. Among them, the blind spot network based methods are the most typical type and have…

We study the influence rules of the speckle size of light source on ghost imaging, and propose a new type of speckle patterns to improve the quality of ghost imaging. The results show that the image quality will first increase and then…

Photoacoustic imaging (PAI) is an emerging non-invasive imaging modality combining the advantages of deep ultrasound penetration and high optical contrast. Image reconstruction is an essential topic in PAI, which is unfortunately an…

We present a new self-supervised deep-learning-based Ghost Imaging (GI) reconstruction method, which provides unparalleled reconstruction quality for noisy acquisitions among unsupervised methods. We present the supporting mathematical…

Currently, single image inpainting has achieved promising results based on deep convolutional neural networks. However, inpainting on stereo images with missing regions has not been explored thoroughly, which is also a significant but…

We present a theoretical study of ghost imaging based on correlated beams arising from parametric down-conversion, and which uses balanced homodyne detection to measure both the signal and idler fields. We analytically show that the…

Modern cameras have limited dynamic ranges and often produce images with saturated or dark regions using a single exposure. Although the problem could be addressed by taking multiple images with different exposures, exposure fusion methods…

We analytically show that it is possible to perform coherent imaging by using the classical correlation of two beams obtained by splitting incoherent thermal radiation. A formal analogy is demonstrated between two such classically…

Multi-spectral imaging, which simultaneously captures the spatial and spectral information of a scene, is widely used across diverse fields, including remote sensing, biomedical imaging, and agricultural monitoring. Here, we introduce a…