Related papers: DynGhost: Temporally-Modelled Transformer for Dyna…
Deep learning has significantly advanced PET image re-construction, achieving remarkable improvements in image quality through direct training on sinogram or image data. Traditional methods often utilize masks for inpainting tasks, but…
We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Previous strategies like image pyramid, multi-scale training, and their variants are aiming at preparing…
Traditional CNN models are trained and tested on relatively low resolution images (<300 px), and cannot be directly operated on large-scale images due to compute and memory constraints. We propose Patch Gradient Descent (PatchGD), an…
By using the ghost imaging technique, we experimentally demonstrate the reconstruction of the diffraction pattern of a {\em pure phase} object by using the classical correlation of incoherent thermal light split on a beam splitter. The…
Ghost imaging is a non local imaging technology, which can obtain target information by measuring the second-order intensity correlation between the reference light field and the target detection light field. However, the current imaging…
Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting. Shadows, highlights, and inter-reflections caused by visible…
Illumination patterns of computational ghost imaging (CGI) systems suffer from reduced contrast when passing through a scattering medium, which causes the effective information in the reconstruction result to be drowned out by noise. A…
Computational temporal ghost imaging (CTGI) allows the reconstruction of a fast signal from a two dimensional detection with no temporal resolution. High speed spatial modulation is implemented to encode temporal detail of the signal into…
High visibility temporal ghost imaging with classical light is possible when superbunching pseudothermal light is employed. In the numerical simulation, the visibility of temporal ghost imaging with pseudothermal light equaling ($4.7\pm…
Convolutional Neural Network is good at image classification. However, it is found to be vulnerable to image quality degradation. Even a small amount of distortion such as noise or blur can severely hamper the performance of these CNN…
We present the first experimental demonstration of ghost imaging realized with intense beams generated by a parametric downconversion interaction seeded with pseudo-thermal light. As expected, the real image of the object is reconstructed…
In quantum mechanics, entanglement and correlations are not just a mere sporadic curiosity, but rather common phenomena at the basis of an interacting quantum system. In electron microscopy, such concepts have not been extensively explored…
The advent of autonomous driving and advanced driver assistance systems necessitates continuous developments in computer vision for 3D scene understanding. Self-supervised monocular depth estimation, a method for pixel-wise distance…
Deep hamming hashing has gained growing popularity in approximate nearest neighbour search for large-scale image retrieval. Until now, the deep hashing for the image retrieval community has been dominated by convolutional neural network…
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…
Reconstructing hand-held objects in 3D from monocular images remains a significant challenge in computer vision. Most existing approaches rely on implicit 3D representations, which produce overly smooth reconstructions and are…
We present an experimental comparison between different iterative ghost imaging algorithms. Our experimental setup utilizes a spatial light modulator for generating known random light fields to illuminate a partially-transmissive object. We…
Image clustering is an important but challenging task in machine learning. As in most image processing areas, the latest improvements came from models based on the deep learning approach. However, classical deep learning methods have…
One primary technical challenge in photoacoustic microscopy (PAM) is the necessary compromise between spatial resolution and imaging speed. In this study, we propose a novel application of deep learning principles to reconstruct…
Visual understanding of the world goes beyond the semantics and flat structure of individual images. In this work, we aim to capture both the 3D structure and dynamics of real-world scenes from monocular real-world videos. Our Dynamic Scene…