Related papers: PISE: Physics-Anchored Semantically-Enhanced Deep …
Reconfigurable intelligent surface (RIS) is a promising candidate technology of the upcoming Sixth Generation (6G) communication system for its ability to provide unprecedented spectral and energy efficiency increment through passive…
Ghost imaging (GI) is an unconventional technique that combines information from two correlated patterned light fields to compute an image of the object of interest. GI can be performed with visible light as well as penetrating radiation…
Modern medical image segmentation methods primarily use discrete representations in the form of rasterized masks to learn features and generate predictions. Although effective, this paradigm is spatially inflexible, scales poorly to…
Physics-informed neural networks (PINNs) constitute a flexible approach to both finding solutions and identifying parameters of partial differential equations. Most works on the topic assume noiseless data, or data contaminated with weak…
As an emerging communication auxiliary technology, reconfigurable intelligent surface (RIS) is expected to play a significant role in the upcoming 6G networks. Due to its total reflection characteristics, it is challenging to implement…
We present GLIMPSE - Gravitational Lensing Inversion and MaPping with Sparse Estimators - a new algorithm to generate density reconstructions in three dimensions from photometric weak lensing measurements. This is an extension of earlier…
A simple and robust experiment demonstrating computational ghost imaging with structured illumination and a single-pixel detector has been performed. Our experimental setup utilizes a general computer for generating pseudo-randomly patterns…
Ghost tomography using single-pixel detection extends the emerging field of ghost imaging to three dimensions, with the use of penetrating radiation. In this work, a series of spatially random x-ray intensity patterns is used to illuminate…
We propose a new grayscale image denoiser, dubbed as Neural Affine Image Denoiser (Neural AIDE), which utilizes neural network in a novel way. Unlike other neural network based image denoising methods, which typically apply simple…
Tractable models of human perception have proved to be challenging to build. Hand-designed models such as MS-SSIM remain popular predictors of human image quality judgements due to their simplicity and speed. Recent modern deep learning…
Pedestrian misalignment, which mainly arises from detector errors and pose variations, is a critical problem for a robust person re-identification (re-ID) system. With bad alignment, the background noise will significantly compromise the…
This work is concerned with discovering the governing partial differential equation (PDE) of a physical system. Existing methods have demonstrated the PDE identification from finite observations but failed to maintain satisfying results…
Ghost imaging (GI) is an unconventional imaging method that retrieves the image of an object by correlating a series of known illumination patterns with the total reflected (or transmitted) intensity. We here demonstrate a scheme which can…
Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-critical systems, such as surveillance cameras, drones and…
Synthesizing images of a person in novel poses from a single image is a highly ambiguous task. Most existing approaches require paired training images; i.e. images of the same person with the same clothing in different poses. However,…
Semantic segmentation models trained on public datasets have achieved great success in recent years. However, these models didn't consider the personalization issue of segmentation though it is important in practice. In this paper, we…
Inferring the physical properties of 3D scenes from visual information is a critical yet challenging task for creating interactive and realistic virtual worlds. While humans intuitively grasp material characteristics such as elasticity or…
Biologically inspired model (BIM) for image recognition is a robust computational architecture, which has attracted widespread attention. BIM can be described as a four-layer structure based on the mechanisms of the visual cortex. Although…
Kernel Density Estimation (KDE) is a cornerstone of nonparametric statistics, yet it remains sensitive to bandwidth choice, boundary bias, and computational inefficiency. This study revisits KDE through a principled convolutional framework,…
In the task of image classification, usually, the network is sensitive to noises. For example, an image of cat with noises might be misclassified as an ostrich. Conventionally, to overcome the problem of noises, one uses the technique of…