Corpus ID: 236428267

Reconstructing Images of Two Adjacent Objects through Scattering Medium Using Generative Adversarial Network

  title={Reconstructing Images of Two Adjacent Objects through Scattering Medium Using Generative Adversarial Network},
  author={Xuetian Lai and Qiongyao Li and Ziyang Chen and Xiaopeng Shao and Jixiong Pu},
Reconstruction of image by using convolutional neural networks (CNNs) has been vigorously studied in the last decade. Until now, there have being developed several techniques for imaging of a single object through scattering medium by using neural networks, however how to reconstruct images of more than one object simultaneously seems hard to realize. In this paper, we demonstrate an approach by using generative adversarial network (GAN) to reconstruct images of two adjacent objects through… Expand

Figures and Tables from this paper


Imaging reconstruction through strongly scattering media by using convolutional neural networks
Abstract As an object passes through strongly scattering slab, it cannot be imaged, due to scattering slab scrambling the object information. In this paper, we employ convolutional neural networkExpand
Mutual Transfer Learning of Reconstructing Images Through a Multimode Fiber or a Scattering Medium
A CNN called as Mobiledense-net (MDN) is developed, which can reconstruct image from the speckle with quite good quality, and it is shown that using a more complex dataset for pre-training, the amount of data forPre-training can be largely reduced and reconstruction quality can be further improved. Expand
Imaging through glass diffusers using densely connected convolutional networks
This work proposes for the first time, to the knowledge, a convolutional neural network architecture called "IDiffNet" for the problem of imaging through diffuse media and demonstrates that IDiffNet has superior generalization capability through extensive tests with well-calibrated diffusers. Expand
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  • C. Ledig, Lucas Theis, +6 authors W. Shi
  • Computer Science, Mathematics
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss. Expand
Deep Learning: High-quality Imaging through Multicore Fiber
A new, strong technique called deep learning is applied to reconstruct the phase image through a multicore fiber in which each core is multimode, and it is shown that the shorter the fiber, the better the imaging quality. Expand
Image-to-Image Translation with Conditional Adversarial Networks
Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. Expand
Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media
This work develops a convolutional neural network (CNN) that is able to learn the statistical information contained in the speckle intensity patterns captured on a set of diffusers having the same macroscopic parameter. Expand
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
Markovian Generative Adversarial Networks (MGANs) are proposed, a method for training generative networks for efficient texture synthesis that surpasses previous neural texture synthesizers by a significant margin and applies to texture synthesis, style transfer, and video stylization. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
Semantic Image Inpainting with Deep Generative Models
A novel method for semantic image inpainting, which generates the missing content by conditioning on the available data, and successfully predicts information in large missing regions and achieves pixel-level photorealism, significantly outperforming the state-of-the-art methods. Expand