Video Compressive Sensing Using Gaussian Mixture Models

Yang, Jianbo; Yuan, Xin; Liao, Xiaozhong; Llull, Patrick; Brady, David J.; Sapiro, Guillermo; Carin, Lawrence

doi:10.1109/tip.2014.2344294

Cited by 207 publications

(156 citation statements)

References 51 publications

Supporting

Mentioning

155

Contrasting

Order By: Relevance

“…Park and Wakin [4] described a coarse-to-fine inverse algorithm which interchanged between temporal motion estimation and spatial video reconstruction in the wavelet domain. Yang et al [5,6] utilized a Gaussian mixture model to represent spatiotemporal video patches, and the video reconstruction can be efficiently calculated based on analytic expressions. In this paper, we extend Gaussian scale mixture (GSM) [7] model to compressive video reconstruction.…”

Section: Introductionmentioning

confidence: 99%

Temporal Compressive Video Reconstruction Using Gaussian Scale Mixture Model

He¹,

Wang²

2017

Proceedings of the International Conference on Computer Networks and Communication Technology (CNCT 2016)

View full text Add to dashboard Cite

Abstract.Compressive sensing has been used to acquire the information in high-frame-rate video using low-frame-rate compressive measurements. Under the framework of coded aperture compressive temporal imaging, we propose a video reconstruction algorithm using Gaussian scale mixture model from temporal compressive measurements. Experimental results demonstrate that our proposed algorithm outperforms state-of-the-art algorithms in both peak signal-to-noise ratio and visual quality.

show abstract

Section: Introductionmentioning

confidence: 99%

Temporal Compressive Video Reconstruction Using Gaussian Scale Mixture Model

He¹,

Wang²

2017

Proceedings of the International Conference on Computer Networks and Communication Technology (CNCT 2016)

View full text Add to dashboard Cite

show abstract

“…Coded aperture imaging techniques have been proposed for a variety of applications [8], [9]. Some of these topologies tackle the extraction of light fields from a scene [5], [7].…”

Section: Introductionmentioning

confidence: 99%

Learning filtered color planes for depth-extraction in coded aperture images

Ochotorena

Dadios

2015

2015 International Conference on Humanoid, Nanotechnology, Information Technology,Communication and Control, Environment and Ma

View full text Add to dashboard Cite

Coded aperture imaging presents an interesting approach to single-image depth extraction. Existing approaches use depth-dependent color misalignment brought about by color coded apertures to calculate the depth map of an image. The depth map itself is not directly calculated from the image but is taken by estimating the disparity for a given shift in the color channels. Earlier measures of color disparity utilized eigenvalue calculations over a sliding window. Such a technique, while effective, is also computationally expensive. In a previous work, we demonstrated that the disparity may be approximated using a variance calculation over a sliding window taken in the YCbCr color space. In this work, we further improve the approximation by learning a suitable filtered color plane that quickly captures the relevant information for disparity estimation. Simulations show the substantial improvement of the proposed color space over eigenvalue-based techniques and the YCbCr space while maintaining low computational cost.Index Terms-color space, filters, depth map, genetic algorithms, computational imaging.

show abstract

“…CS approaches have been shown to reduce dose by as much as 90% in electron microscopy [2,3,4]. Optical imaging and microscopy have also seen substantial benefits [5,6,7,8,9,10,11,12,13]. This tutorial will briefly introduce the principles of CS.…”

mentioning

confidence: 99%