Related papers: Compressed ghost edge imaging
This paper presents Deep Networks for Improved Segmentation Edges (DeNISE), a novel data enhancement technique using edge detection and segmentation models to improve the boundary quality of segmentation masks. DeNISE utilizes the inherent…
We study the imaging of a penetrable scatterer, aka target, in a waveguide with randomly perturbed boundary. The target is located between a partially coherent source which transmits the wave, and a detector which measures the spatially…
The image information acquisition ability of a conventional camera is usually much lower than the Shannon Limit since it does not make use of the correlation between pixels of image data. Applying a random phase modulator to code the…
Correspondence imaging can achieve positive-negative ghost images by just conditional averaging of partial patterns, without treating bucket intensities as weights. To explain its imaging mechanism, we develop a probability theory assuming…
Lenses that can collect the perfect image of an object must restore propagative and evanescent waves. However, for efficient information transfer, e.g., in compressed sensing, it is often desirable to detect only the fast spatial variations…
We experimentally demonstrate pseudothermal ghost imaging and ghost diffraction using only a single single-pixel detector. We achieve this by replacing the high resolution detector of the reference beam with a computation of the propagating…
Ultrasound image compression by preserving speckle-based key information is a challenging task. In this paper, we introduce an ultrasound image compression framework with the ability to retain realism of speckle appearance despite achieving…
We experimentally demonstrated a spectral imaging scheme with dual compressed sensing. With the dimensions of spectral and spatial information both compressed, the spectral image of a colored object can be obtained with only a single point…
In this Letter, we report a demonstration of ion and electron ghost imaging. Two beams of correlated ions and electrons are produced by a photoionization process and accelerated into opposite directions. Using a single time and position…
Textureless object recognition has become a significant task in Computer Vision with the advent of Robotics and its applications in manufacturing sector. It has been challenging to obtain good accuracy in real time because of its lack of…
We develop a concept of metasurface-assisted ghost imaging for non-local discrimination between a set of polarization objects. The specially designed metasurfaces are incorporated in the imaging system to perform parallel state…
The Gaussian splatting methods are getting popular. However, their loss function only contains the $\ell_1$ norm and the structural similarity between the rendered and input images, without considering the edges in these images. It is…
For tiny obstacle discovery in a monocular image, edge is a fundamental visual element. Nevertheless, because of various reasons, e.g., noise and similar color distribution with background, it is still difficult to detect the edges of tiny…
In this paper we introduce a system for unsupervised object discovery and segmentation of RGBD-images. The system models the sensor noise directly from data, allowing accurate segmentation without sensor specific hand tuning of measurement…
The objective of this paper is to learn a compact representation of image sets for template-based face recognition. We make the following contributions: first, we propose a network architecture which aggregates and embeds the face…
The inability of automated edge detection methods inspired from primal sketch models to accurately calculate object edges under the influence of pixel noise is an open problem. Extending the principles of image perception i.e. Weber-Fechner…
We introduce a novel masked graph autoencoder (MGAE) framework to perform effective learning on graph structure data. Taking insights from self-supervised learning, we randomly mask a large proportion of edges and try to reconstruct these…
Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…
The use of x-ray imaging in medicine and other research is well known. Generally, the image quality is proportional to the total flux, but high photon energy could severely damage the specimen, so how to decrease the radiation dose while…
For ghost imaging, pursuing high resolution images and short acquisition times required for reconstructing images are always two main goals. We report an image reconstruction algorithm called compressive sampling (CS) reconstruction to…