Hyperspectral Compressive Sensing Using Manifold-Structured Sparsity Prior

Zhang, Lei; Wei, Wei; Zhang, Yanning; Li, Fēi; Shen, Chunhua; Shi, Qinfeng

doi:10.1109/iccv.2015.405

Cited by 15 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, CS color video and depth recovery used both wavelet and DCT [42]. Hyperspectral imaging utilized manifold-structured sparsity prior [45] or reweighted Laplace prior [46]. Self-similarity in images is also used as a prior for CS image recovery such as NLR-CS [13] and denoiser based AMP (D-AMP) [30].…”

Section: Conventional Compressive Image Recoverymentioning

confidence: 99%

“…Compressive sensing (CS) has provided ways to sample and to compress signals at the same time with relatively long signal reconstruction time [9,14]. The idea of combining image acquisition and compression immediately drew great attention in the application areas such as MRI [27,34], CT [10], hyperspectral imaging [45,46], coded aperture imaging [2], radar imaging [32] and radio astronomy [37]. Ground Truth TVAL3 (35.74 dB) Proposed (38.67 dB) Figure 1: Ground truth MR image from fully-sampled data (left), reconstructed MR images from 50%-sampled data using conventional TV image prior (middle, [27]) and our proposed deep learning based method without ground truth (right).…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior

Zhussip

Soltanayev

Chun

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Compressive sensing is a method to recover the original image from undersampled measurements. In order to overcome the ill-posedness of this inverse problem, image priors are used such as sparsity in the wavelet domain, minimum total-variation, or self-similarity. Recently, deep learning based compressive image recovery methods have been proposed and have yielded state-of-the-art performances. They used deep learning based data-driven approaches instead of hand-crafted image priors to solve the ill-posed inverse problem with undersampled data. Ironically, training deep neural networks for them requires "clean" ground truth images, but obtaining the best quality images from undersampled data requires well-trained deep neural networks. To resolve this dilemma, we propose novel methods based on two well-grounded theories: denoiser-approximate message passing and Stein's unbiased risk estimator. Our proposed methods were able to train deep learning based image denoisers from undersampled measurements without ground truth images and without image priors, and to recover images with state-of-the-art qualities from undersampled data. We evaluated our methods for various compressive sensing recovery problems with Gaussian random, coded diffraction pattern, and compressive sensing MRI measurement matrices. Our methods yielded state-of-theart performances for all cases without ground truth images and without image priors. They also yielded comparable performances to the methods with ground truth data.

show abstract

Section: Conventional Compressive Image Recoverymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior

Zhussip

Soltanayev

Chun

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…A hyperspectral image (HSI) consists of various intensities that represent the integrals of the radiance captured by sensors over hundreds of discrete bands. As compared with traditional image systems, HSI facilitates delivering more faithful representation for real scenes, and thus tends to be better performed on various computer vision tasks, such as classification [54], super-resolution [16], compressed sensing [53,32], and mineral exploration [48,21].…”

Section: Introductionmentioning

confidence: 99%

Enhanced 3DTV Regularization and Its Applications on Hyper-spectral Image Denoising and Compressed Sensing

Peng,

Xie,

Zhao

et al. 2018

Preprint

View full text Add to dashboard Cite

The 3-D total variation (3DTV) is a powerful regularization term, which encodes the local smoothness prior structure underlying a hyper-spectral image (HSI), for general HSI processing tasks. This term is calculated by assuming identical and independent sparsity structures on all bands of gradient maps calculated along spatial and spectral HSI modes. This, however, is always largely deviated from the real cases, where the gradient maps are generally with different while correlated sparsity structures across all their bands. Such deviation tends to hamper the performance of the related method by adopting such prior term. To this issue, this paper proposes an enhanced 3DTV (E-3DTV) regularization term beyond conventional 3DTV. Instead of imposing sparsity on gradient maps themselves, the new term calculated sparsity on the subspace bases on the gradient maps along their bands, which naturally encode the correlation and difference across these bands, and more faithfully reflect the insightful configurations of an HSI. The E-3DTV term can easily replace the previous 3DTV term and be embedded into an HSI processing model to ameliorate its performance. The superiority of the proposed methods is substantiated by extensive experiments on two typical related tasks: HSI denoising and compressed sensing, as compared with state-of-the-arts designed for both tasks.

show abstract

Cluster Sparsity Field: An Internal Hyperspectral Imagery Prior for Reconstruction

et al. 2018

View full text Add to dashboard Cite

Hyperspectral Compressive Sensing Using Manifold-Structured Sparsity Prior

Cited by 15 publications

References 26 publications

Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior

Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior

Enhanced 3DTV Regularization and Its Applications on Hyper-spectral Image Denoising and Compressed Sensing

Cluster Sparsity Field: An Internal Hyperspectral Imagery Prior for Reconstruction

Contact Info

Product

Resources

About