scholarly journals Holographic Optical Field Recovery Using a Regularized Untrained Deep Decoder Network

2021 ◽  
Author(s):  
Farhad Niknam ◽  
Hamed Ghazvini ◽  
Hamid Latifi
Keyword(s):  
Computational Imaging ◽  
Training Dataset ◽  
Reconstruction Method ◽  
Single Shot ◽  
Sample Type ◽  
Lack Of Information ◽  
Image Prior ◽  
Measured Information ◽  
Image Priors ◽  
Training Resources

Abstract Image reconstruction using minimal measured information has been a long-standing open problem in many computational imaging approaches, in particular in-line holography. Many solutions are devised based on compressive sensing (CS) techniques with handcrafted image priors or supervised Deep Neural Networks (DNN). However, the limited performance of CS methods due to lack of information about the image priors and the requirement of an enormous amount of per-sample-type training resources for DNNs has posed new challenges over the primary problem. In this study, we propose a single-shot lensless in-line holographic reconstruction method using an untrained deep neural network which is incorporated with a physical image formation algorithm. We demonstrate that by modifying a deep decoder network with simple regularizers, a Gabor hologram can be inversely reconstructed via a minimization process that is constrained by a deep image prior. The outcoming model allows to accurately recover the phase and amplitude images without any training dataset, excess measurements, or specific assumptions about the object’s or the measurement’s characteristics.

scholarly journals Holographic optical field recovery using a regularized untrained deep decoder network

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Farhad Niknam ◽  
Hamed Qazvini ◽  
Hamid Latifi
Keyword(s):  
Computational Imaging ◽  
Training Dataset ◽  
Reconstruction Method ◽  
Single Shot ◽  
Sample Type ◽  
Lack Of Information ◽  
Image Prior ◽  
Measured Information ◽  
Image Priors ◽  
Training Resources

AbstractImage reconstruction using minimal measured information has been a long-standing open problem in many computational imaging approaches, in particular in-line holography. Many solutions are devised based on compressive sensing (CS) techniques with handcrafted image priors or supervised deep neural networks (DNN). However, the limited performance of CS methods due to lack of information about the image priors and the requirement of an enormous amount of per-sample-type training resources for DNNs has posed new challenges over the primary problem. In this study, we propose a single-shot lensless in-line holographic reconstruction method using an untrained deep neural network which is incorporated with a physical image formation algorithm. We demonstrate that by modifying a deep decoder network with simple regularizers, a Gabor hologram can be inversely reconstructed via a minimization process that is constrained by a deep image prior. The outcoming model allows to accurately recover the phase and amplitude images without any training dataset, excess measurements, or specific assumptions about the object’s or the measurement’s characteristics.

scholarly journals Ecosystem–atmosphere exchange of microorganisms in a Mediterranean grassland: new insights into microbial flux through a combined experimental-modeling approach

2017 ◽  
Author(s):  
Federico Carotenuto ◽  
Teodoro Georgiadis ◽  
Beniamino Gioli ◽  
Christel Leyronas ◽  
Cindy E. Morris ◽  
...  
Keyword(s):  
Deterministic Model ◽  
Point Of View ◽  
Cloud Formation ◽  
Training Dataset ◽  
Promising Tool ◽  
Biological Aerosols ◽  
Ice Nuclei ◽  
Lack Of Information ◽  
Bacteria And Fungi ◽  
The Impact

Abstract. Microbial aerosols (mainly composed by bacterial and fungal cells), may constitute up to 74 % of the total aerosol volume. These biological aerosols are relevant not only from the point of view of the dispersion of pathogenic species, but also due to the potential geochemical implications. Some bacteria and fungi may, in fact, serve as cloud condensation or ice nuclei, potentially affecting cloud formation and precipitation and are active at higher temperatures compared to their, much more intensively studied, inorganic counterparts. Simulations of the impact of microbial aerosols on climate are still hindered by the lack of information regarding their emissions from ground sources. This work tackles this knowledge gap by (i) applying a rigorous micrometeorological approach to the estimation of microbial net fluxes above a Mediterranean grassland and (ii) developing a deterministic model to estimate these emissions on the basis of a few easily recovered meteorological parameters (the PLAnET model). The grassland itself is characterized by an abundance of positive net microbial fluxes and the model proves to be a promising tool capable of capturing the day-to-day variability in microbial fluxes with a relatively small bias and sufficient accuracy. PLAnET is still in its infancy and will benefit from future campaigns extending the available training dataset as well as the inclusion of ever more complex and critical phenomena affecting the release of microbial aerosol (such as rainfall). The model itself is also adaptable as an emission module for dispersion and chemical transport models, allowing to further explore the impact of microbial aerosols on the atmosphere and climate.

scholarly journals Efficient Training Procedures for Multi-Spectral Demosaicing

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2850
Author(s):  
Ivana Shopovska ◽  
Ljubomir Jovanov ◽  
Wilfried Philips
Keyword(s):  
Near Infrared ◽  
Current Model ◽  
General Term ◽  
Training Data ◽  
Data Selection ◽  
Training Dataset ◽  
Single Shot ◽  
Training Procedure ◽  
Robust Model ◽  
Using Data

The simultaneous acquisition of multi-spectral images on a single sensor can be efficiently performed by single shot capture using a mutli-spectral filter array. This paper focused on the demosaicing of color and near-infrared bands and relied on a convolutional neural network (CNN). To train the deep learning model robustly and accurately, it is necessary to provide enough training data, with sufficient variability. We focused on the design of an efficient training procedure by discovering an optimal training dataset. We propose two data selection strategies, motivated by slightly different concepts. The general term that will be used for the proposed models trained using data selection is data selection-based multi-spectral demosaicing (DSMD). The first idea is clustering-based data selection (DSMD-C), with the goal to discover a representative subset with a high variance so as to train a robust model. The second is an adaptive-based data selection (DSMD-A), a self-guided approach that selects new data based on the current model accuracy. We performed a controlled experimental evaluation of the proposed training strategies and the results show that a careful selection of data does benefit the speed and accuracy of training. We are still able to achieve high reconstruction accuracy with a lightweight model.

scholarly journals Single-Shot 3D Multi-Person Shape Reconstruction from a Single RGB Image

Entropy ◽  
2020 ◽  
Vol 22 (8) ◽  
pp. 806
Author(s):  
Seong Hyun Kim ◽  
Ju Yong Chang
Keyword(s):  
Coordinate System ◽  
Shape Reconstruction ◽  
Reconstruction Method ◽  
Single Shot ◽  
3D Shape ◽  
End To End ◽  
The Absolute ◽  
3D Shapes ◽  
Camera Coordinate System ◽  
Rgb Image

Although the performance of the 3D human shape reconstruction method has improved considerably in recent years, most methods focus on a single person, reconstruct a root-relative 3D shape, and rely on ground-truth information about the absolute depth to convert the reconstruction result to the camera coordinate system. In this paper, we propose an end-to-end learning-based model for single-shot, 3D, multi-person shape reconstruction in the camera coordinate system from a single RGB image. Our network produces output tensors divided into grid cells to reconstruct the 3D shapes of multiple persons in a single-shot manner, where each grid cell contains information about the subject. Moreover, our network predicts the absolute position of the root joint while reconstructing the root-relative 3D shape, which enables reconstructing the 3D shapes of multiple persons in the camera coordinate system. The proposed network can be learned in an end-to-end manner and process images at about 37 fps to perform the 3D multi-person shape reconstruction task in real time.

scholarly journals AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compression

2021 ◽  
Author(s):  
Baozhou Zhu ◽  
Peter Hofstee ◽  
Johan Peltenburg ◽  
Jinho Lee ◽  
Zaid Alars
Keyword(s):  
Experimental Results ◽  
Training Dataset ◽  
Reconstruction Method ◽  
Original Training ◽  
Neural Architecture ◽  
Reconstruction Methods ◽  
Network Engineering ◽  
Current Reconstruction

Data-free compression raises a new challenge because the original training dataset for a pre-trained model to be compressed is not available due to privacy or transmission issues. Thus, a common approach is to compute a reconstructed training dataset before compression. The current reconstruction methods compute the reconstructed training dataset with a generator by exploiting information from the pre-trained model. However, current reconstruction methods focus on extracting more information from the pre-trained model but do not leverage network engineering. This work is the first to consider network engineering as an approach to design the reconstruction method. Specifically, we propose the AutoReCon method, which is a neural architecture search-based reconstruction method. In the proposed AutoReCon method, the generator architecture is designed automatically given the pre-trained model for reconstruction. Experimental results show that using generators discovered by the AutoRecon method always improve the performance of data-free compression.

scholarly journals Deep Learning- and Transfer Learning-Based Super Resolution Reconstruction from Single Medical Image

2017 ◽  
Vol 2017 ◽  
pp. 1-20 ◽  
Author(s):  
YiNan Zhang ◽  
MingQiang An
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Medical Images ◽  
Super Resolution ◽  
Training Dataset ◽  
Reconstruction Method ◽  
Hybrid Architecture ◽  
Learning Approaches ◽  
Training Samples ◽  
Bicubic Interpolation

Medical images play an important role in medical diagnosis and research. In this paper, a transfer learning- and deep learning-based super resolution reconstruction method is introduced. The proposed method contains one bicubic interpolation template layer and two convolutional layers. The bicubic interpolation template layer is prefixed by mathematics deduction, and two convolutional layers learn from training samples. For saving training medical images, a SIFT feature-based transfer learning method is proposed. Not only can medical images be used to train the proposed method, but also other types of images can be added into training dataset selectively. In empirical experiments, results of eight distinctive medical images show improvement of image quality and time reduction. Further, the proposed method also produces slightly sharper edges than other deep learning approaches in less time and it is projected that the hybrid architecture of prefixed template layer and unfixed hidden layers has potentials in other applications.

scholarly journals Reference-Driven Compressed Sensing MR Image Reconstruction Using Deep Convolutional Neural Networks without Pre-Training

Sensors ◽  
2020 ◽  
Vol 20 (1) ◽  
pp. 308 ◽  
Author(s):  
Di Zhao ◽  
Feng Zhao ◽  
Yongjin Gan
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Compressed Sensing ◽  
Training Dataset ◽  
Reconstruction Method ◽  
Training Procedure ◽  
Deep Convolutional Neural Networks ◽  
Mr Image ◽  
Space Data ◽  
Mr Image Reconstruction

Deep learning has proven itself to be able to reduce the scanning time of Magnetic Resonance Imaging (MRI) and to improve the image reconstruction quality since it was introduced into Compressed Sensing MRI (CS-MRI). However, the requirement of using large, high-quality, and patient-based datasets for network training procedures is always a challenge in clinical applications. In this paper, we propose a novel deep learning based compressed sensing MR image reconstruction method that does not require any pre-training procedure or training dataset, thereby largely reducing clinician dependence on patient-based datasets. The proposed method is based on the Deep Image Prior (DIP) framework and uses a high-resolution reference MR image as the input of the convolutional neural network in order to induce the structural prior in the learning procedure. This reference-driven strategy improves the efficiency and effect of network learning. We then add the k-space data correction step to enforce the consistency of the k-space data with the measurements, which further improve the image reconstruction accuracy. Experiments on in vivo MR datasets showed that the proposed method can achieve more accurate reconstruction results from undersampled k-space data.

scholarly journals Mid-Infrared Compressive Hyperspectral Imaging

2021 ◽  
Vol 13 (4) ◽  
pp. 741
Author(s):  
Shuowen Yang ◽  
Xiang Yan ◽  
Hanlin Qin ◽  
Qingjie Zeng ◽  
Yi Liang ◽  
...  
Keyword(s):  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Side Information ◽  
Computational Imaging ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Acquisition Time ◽  
Reconstruction Method ◽  
Mid Infrared ◽  
Spectral Channels

Hyperspectral imaging (HSI) has been widely investigated within the context of computational imaging due to the high dimensional challenges for direct imaging. However, existing computational HSI approaches are mostly designed for the visible to near-infrared waveband, whereas less attention has been paid to the mid-infrared spectral range. In this paper, we report a novel mid-infrared compressive HSI system to extend the application domain of mid-infrared digital micromirror device (MIR-DMD). In our system, a modified MIR-DMD is combined with an off-the-shelf infrared spectroradiometer to capture the spatial modulated and compressed measurements at different spectral channels. Following this, a dual-stage image reconstruction method is developed to recover infrared hyperspectral images from these measurements. In addition, a measurement without any coding is used as the side information to aid the reconstruction to enhance the reconstruction quality of the infrared hyperspectral images. A proof-of-concept setup is built to capture the mid-infrared hyperspectral data of 64 pixels × 48 pixels × 100 spectral channels ranging from 3 to 5 μm, with the acquisition time within one minute. To the best of our knowledge, this is the first mid-infrared compressive hyperspectral imaging approach that could offer a less expensive alternative to conventional mid-infrared hyperspectral imaging systems.

Sign in / Sign up

Export Citation Format

Share Document