Related papers: Ghost Imaging Based on Recurrent Neural Network

This paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs (RAGs), in which regions are superpixels and edges connect neighboring…

Abrupt learning is a common phenomenon in recurrent neural networks (RNNs) trained on working memory tasks. In such cases, the networks develop transient slow regions in state space that extend the effective timescales of computation.…

Ghost imaging (GI) is a novel imaging method, which can reconstruct the object information by the light intensity correlation measurements. However, at present, the field of view (FOV) is limited to the illuminating range of the light…

Computational ghost imaging generally requires a large number of pattern illumination to obtain a high-quality image. The colored noise speckle pattern was recently proposed to substitute the white noise pattern in a variety of noisy…

To address the sequential changes of images including poses, in this paper we propose a recurrent regression neural network(RRNN) framework to unify two classic tasks of cross-pose face recognition on still images and video-based face…

Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that…

The nature of multiple samples to extract correlation information limits the applications of ghost imaging of moving objects. A novel multi-to-one neural network is proposed and the concept of "batch frame" is introduced to improve the…

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…

Video snapshot compressive imaging (SCI) utilizes a 2D detector to capture sequential video frames and compress them into a single measurement. Various reconstruction methods have been developed to recover the high-speed video frames from…

Recent research on image denoising has progressed with the development of deep learning architectures, especially convolutional neural networks. However, real-world image denoising is still very challenging because it is not possible to…

X-ray Fluorescence Ghost Imaging (XRF-GI) was recently demonstrated for x-ray lab sources. It has the potential to reduce acquisition time and deposited dose by choosing their trade-off with spatial resolution, while alleviating the…

We propose Neural Image Compression (NIC), a two-step method to build convolutional neural networks for gigapixel image analysis solely using weak image-level labels. First, gigapixel images are compressed using a neural network trained in…

Deep-neural-network-based image reconstruction has demonstrated promising performance in medical imaging for under-sampled and low-dose scenarios. However, it requires large amount of memory and extensive time for the training. It is…

Custom and natural lighting conditions can be emulated in images of the scene during post-editing. Extraordinary capabilities of the deep learning framework can be utilized for such purpose. Deep image relighting allows automatic photo…

In this paper, we present GaNI, a Global and Near-field Illumination-aware neural inverse rendering technique that can reconstruct geometry, albedo, and roughness parameters from images of a scene captured with co-located light and camera.…

Implicit Neural Representations (INRs) are widely used for modeling continuous 2D images, enabling high-fidelity reconstruction, super-resolution, and compression. Architectures such as SIREN, WIRE, and FINER demonstrate their ability to…

Computer-generated hologram (CGH) allows for the on-demand scaling and projection of artificially designed target patterns, while incorporating benefits such as a lensless setup and high-frame-rate operation. In this work, we actively…

X-ray based imaging modalities are widely used in research, industry, and in the medical field. Consequently, there is a strong motivation to improve their performances with respect to resolution, dose, and contrast. Ghost imaging (GI) is…

We integrate the recently proposed spatial transformer network (SPN) [Jaderberg et. al 2015] into a recurrent neural network (RNN) to form an RNN-SPN model. We use the RNN-SPN to classify digits in cluttered MNIST sequences. The proposed…

Recurrent Neural Networks (RNNs) achieve state-of-the-art results in many sequence-to-sequence modeling tasks. However, RNNs are difficult to train and tend to suffer from overfitting. Motivated by the Data Processing Inequality (DPI), we…