DeepBinaryMask: Learning a Binary Mask for Video Compressive Sensing

Iliadis, Michael; Spinoulas, Leonidas; Katsaggelos, Aggelos K.

doi:10.48550/arxiv.1607.03343

Cited by 5 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For compressive video recovery, Iliadis etal. [23], [24] propose Deep Fully-Connected Network, where the encoder learns binary sensing mask and the decoder determines the reconstruction of the video. These approaches effectively avoid the expensive computation in traditional approaches and have achieved promising image/video reconstruction performance.…”

Section: Related Workmentioning

confidence: 99%

DR2-Net: Deep Residual Reconstruction Network for image compressive sensing

et al. 2019

View full text Add to dashboard Cite

Most traditional algorithms for compressive sensing image reconstruction suffer from the intensive computation. Recently, deep learning-based reconstruction algorithms have been reported, which dramatically reduce the time complexity than iterative reconstruction algorithms. In this paper, we propose a novel Deep Residual Reconstruction Network (DR 2 -Net) to reconstruct the image from its Compressively Sensed (CS) measurement. The DR 2 -Net is proposed based on two observations: 1) linear mapping could reconstruct a high-quality preliminary image, and 2) residual learning could further improve the reconstruction quality. Accordingly, DR 2 -Net consists of two components, i.e., linear mapping network and residual network, respectively. Specifically, the fully-connected layer in neural network implements the linear mapping network. We then expand the linear mapping network to DR 2 -Net by adding several residual learning blocks to enhance the preliminary image. Extensive experiments demonstrate that the DR 2 -Net outperforms traditional iterative methods and recent deep learning-based methods by large margins at measurement rates 0.01, 0.04, 0.1, and 0.25, respectively. The code of DR 2 -Net has been released on: https://github.com/coldrainyht/caffe dr2 33 33 33 33 33 33 64 32 1 Block CS Measurements Linear Mapping Residual Learning Block

show abstract

Section: Related Workmentioning

confidence: 99%

DR2-Net: Deep Residual Reconstruction Network for image compressive sensing

et al. 2019

View full text Add to dashboard Cite

show abstract

“…A reinforcement learning based auto focus method has been proposed in [195]. Taking one step further, the sampling in video compressive imaging can be optimized to achieve sufficient spatio-temporal sampling of sequential frames at the maximal capturing speed [196], and learning the sensing matrix to optimize the mask can further improve the quality of the compressive sensing reconstruction algorithm [197].…”

Section: A Ai Improves Quality and Efficiency Of CI Systemmentioning

confidence: 99%

Computational Imaging and Artificial Intelligence: The Next Revolution of Mobile Vision

Suo¹,

Zhang²,

Gong³

et al. 2021

Preprint

View full text Add to dashboard Cite

Signal capture stands in the forefront to perceive and understand the environment and thus imaging plays the pivotal role in mobile vision. Recent explosive progresses in Artificial Intelligence (AI) have shown great potential to develop advanced mobile platforms with new imaging devices. Traditional imaging systems based on the "capturing images first and processing afterwards" mechanism cannot meet this unprecedented demand. Differently, Computational Imaging (CI) systems are designed to capture high-dimensional data in an encoded manner to provide more information for mobile vision systems. Thanks to AI, CI can now be used in real systems by integrating deep learning algorithms into the mobile vision platform to achieve the closed loop of intelligent acquisition, processing and decision making, thus leading to the next revolution of mobile vision. Starting from the history of mobile vision using digital cameras, this work first introduces the advances of CI in diverse applications and then conducts a comprehensive review of current research topics combining CI and AI. Motivated by the fact that most existing studies only loosely connect CI and AI (usually using AI to improve the performance of CI and only limited works have deeply connected them), in this work, we propose a framework to deeply integrate CI and AI by using the example of self-driving vehicles with high-speed communication, edge computing and traffic planning. Finally, we outlook the future of CI plus AI by investigating new materials, brain science and new computing techniques to shed light on new directions of mobile vision systems.

show abstract

“…Yet, with sufficient CS-sampled and original signal data available, a rather fastto-query DL reconstruction model can be built. Using DL for signal reconstruction (b) has, thus been successfully demonstrated in numerous domains [49,55,64,69,119,139]. The performance of such solutions not only matched, but also significantly exceeded the performance of the standard reconstruction approaches as additional signal structure can be captured by generative DL models [41,90,106,114].…”

Section: Towards Deep Learning-supported Compressive Sensingmentioning

confidence: 99%

“…This was later enhanced with a modified loss function -in [166] the authors moved from a generally-applicable mean squared error to image-specific structural similarity index measure (SSIM) as a training loss function for the autoencoder. Adapting to the domain is also evident in [55] where Iliadis et al developed a DL architecture for compressive sensing and reconstruction of temporal video. Another adaptation [95] was designed for the particularities of the biological signals.…”

Section: Autoencoder-based Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Techniques for Compressive Sensing-Based Reconstruction and Inference -- A Ubiquitous Systems Perspective

Machidon,

Pejovic

2021

Preprint

View full text Add to dashboard Cite

Compressive sensing (CS) is a mathematically elegant tool for reducing the sampling rate, potentially bringing contextawareness to a wider range of devices. Nevertheless, practical issues with the sampling and reconstruction algorithms prevent further proliferation of CS in real world domains, especially among heterogeneous ubiquitous devices. Deep learning (DL) naturally complements CS for adapting the sampling matrix, reconstructing the signal, and learning form the compressed samples. While the CS-DL integration has received substantial research interest recently, it has not yet been thoroughly surveyed, nor has the light been shed on practical issues towards bringing the CS-DL to real world implementations in the ubicomp domain. In this paper we identify main possible ways in which CS and DL can interplay, extract key ideas for making CS-DL efficient, identify major trends in CS-DL research space, and derive guidelines for future evolution of CS-DL within the ubicomp domain. CCS Concepts: • Computer systems organization → Sensor networks; • Human-centered computing → Ubiquitous computing; • Computing methodologies → Neural networks.

show abstract

DeepBinaryMask: Learning a Binary Mask for Video Compressive Sensing

Cited by 5 publications

References 0 publications

DR2-Net: Deep Residual Reconstruction Network for image compressive sensing

DR2-Net: Deep Residual Reconstruction Network for image compressive sensing

Computational Imaging and Artificial Intelligence: The Next Revolution of Mobile Vision

Deep Learning Techniques for Compressive Sensing-Based Reconstruction and Inference -- A Ubiquitous Systems Perspective

Contact Info

Product

Resources

About