Related papers: Computational ghost imaging using deep learning

Ghost imaging has been receiving increasing interest for possible use as a remote-sensing system. There has been little comparison, however, between ghost imaging and the imaging laser radars with which it would be competing. Toward that…

Ghost projection is the reversed process of computational classical ghost imaging that allows any desired image to be synthesized using a linear combination of illuminating patterns. Typically, physical attenuating masks are used to produce…

Imaging the full-field microvibration of extended targets remains a formidable challenge for conventional remote sensing. Traditional array-based sensors are often severely constrained by data throughput and sensitivity limits when scaling…

The rapid development of deep learning techniques has created new challenges in identifying the origin of digital images because generative adversarial networks and variational autoencoders can create plausible digital images whose contents…

Ghost imaging is a quantum optics technique that uses correlations between two beams to reconstruct an image in one beam from photons that do not interact with the object being imaged. While pairwise (second order) correlations are usually…

We present a protocol for the amplification and distribution of a one-time-pad cryptographic key over a point-to-multipoint optical network based on computational ghost imaging (GI) and compressed sensing (CS). It is shown experimentally…

Image denoising methods must effectively model, implicitly or explicitly, the vast diversity of patterns and textures that occur in natural images. This is challenging, even for modern methods that leverage deep neural networks trained to…

Spectral camera based on ghost imaging via sparsity constraints (GISC spectral camera) obtains three-dimensional (3D) hyperspectral information with two-dimensional (2D) compressive measurements in a single shot, which has attracted much…

Recent work has indicated that ghost imaging may have applications in standoff sensing. However, most theoretical work has addressed transmission-based ghost imaging. To be a viable remote-sensing system, the ghost imager needs to image…

Single-pixel imaging (SPI) is a novel imaging technique whose working principle is based on the compressive sensing (CS) theory. In SPI, data is obtained through a series of compressive measurements and the corresponding image is…

Distinguishing between computer-generated (CG) and natural photographic (PG) images is of great importance to verify the authenticity and originality of digital images. However, the recent cutting-edge generation methods enable high…

Conventional imaging at low light level requires hundreds of detected photons per pixel to suppress the Poisson noise for accurate reflectivity inference. In this letter, we propose a high-efficiency photon-limited imaging technique, called…

Ghost imaging enables the imaging of an object using intensity correlations between a single-pixel detector placed behind the object and a camera that records light that did not interact with the object. The object and the camera are often…

Imaging and edge detection have been widely applied and played an important role in security checking and medical diagnosis. However, as we know, most edge detection based on ghost imaging system require a large measurement times and the…

We present a robust imaging method based on time-correspondence imaging and normalized ghost imaging (GI) that sets two thresholds to select the reference frame exposures for image reconstruction. This double-threshold time-correspondence…

Deep learning techniques have received much attention in the area of image denoising. However, there are substantial differences in the various types of deep learning methods dealing with image denoising. Specifically, discriminative…

Ghost imaging and differential ghost imaging are well-known imaging techniques based on the use of both classical and quantum correlated states of light. Since the existence of correlations has been shown to be the main resource to…

Computational image reconstruction algorithms generally produce a single image without any measure of uncertainty or confidence. Regularized Maximum Likelihood (RML) and feed-forward deep learning approaches for inverse problems typically…

Classical convolutional neural networks (cCNNs) are very good at categorizing objects in images. But, unlike human vision which is relatively robust to noise in images, the performance of cCNNs declines quickly as image quality worsens.…

We offer new illumination patterns for imaging in all-digital ghost imaging (GI) systems. The digital patterns, written as computer generated holograms on spatial light modulators (SLM), are generated by the Ising model, a well-known…