HSCNN: CNN-Based Hyperspectral Image Recovery from Spectrally Undersampled Projections

Xiong, Zhiwei; Shi, Zhan; Li, Huiqun; Wang, Lizhi; Liu, Dong; Wu, Feng

doi:10.1109/iccvw.2017.68

Cited by 190 publications

(110 citation statements)

References 25 publications

Supporting

Mentioning

100

Contrasting

Order By: Relevance

“…We also evaluated the MSFAs by using deep-learning-based spectral reconstruction method, such as the HSCNN method [27], which won the NTIRE spectral reconstruction contest [29] recently. Our designed MSFA still outperformother MSFAs although the reconstruction method has been changed.…”

Section: Resultsmentioning

confidence: 99%

“…Based on sparse reconstruction, some literature has proved that the reconstruction accuracy would benefit from combining the prior of local manifold structure [16,26]. To further improve reconstruction quality, the convolutional neural network based learning methods which utilize the spatial information of images have begun to appear [27,28]. Various network structures have been proposed for a contest to show the potential of deep learning in spectral construction [29].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Optimized Multi-Spectral Filter Arrays for Spectral Reconstruction

Xie

et al. 2019

Sensors

View full text Add to dashboard Cite

Multispectral filter array (MSFA)-based imaging is a compact, practical technique for snapshot spectral image capturing and reconstruction. The imaging and reconstruction quality is highly influenced by the spectral sensitivities and spatial arrangement of channels on MSFAs, and the used reconstruction method. In order to design a MSFA with high imaging capacity, we propose a sparse representation based approach to optimize spectral sensitivities and spatial arrangement of MSFAs. The proposed approach first overall models the various errors associated with spectral reconstruction, and then uses a global heuristic searching method to optimize MSFAs via minimizing the estimated error of MSFAs. Our MSFA optimization method can select filters from off-the-shelf candidate filter sets while assigning the selected filters to the designed MSFA. Experimental results on three datasets show that the proposed method is more efficient, flexible, and can design MSFAs with lower spectral construction errors when compared with existing state-of-the-art methods. The MSFAs designed by our method show better performance than others even using different spectral reconstruction methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Optimized Multi-Spectral Filter Arrays for Spectral Reconstruction

Xie

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…They claimed their results significantly improved the state-of-theart. [11] In 2018, by removing the hand-crafted upsampling in HSCNN, Zhan et al developed HSCNN+, which has two kinds of networks, HSCNN-R and HSCNN-D. HSCNN-R consists of several residual blocks, and HSCNN-D replaces the residual blocks by a dense block with a novel fusion scheme [12]. In the NTIRE 2018 Spectral Reconstruction Challenge, HSCNN-D ranked first, and HSCNN-R ranked second [13].…”

Section: Related Workmentioning

confidence: 99%

Multispectral Image Reconstruction From Color Images Using Enhanced Variational Autoencoder and Generative Adversarial Network

et al. 2021

View full text Add to dashboard Cite

“…In the context of Compressed Sensing, Yuann et al [87] consider the super-resolution of observations acquired by a Compressed Sensing architectures, specifically the CASSI [88], using CNN architectures, which allow demonstrates promising performance under simulated conditions. A similar approach involving the recovery of HS observations from Compressed Sensing measurements is also considered in [89], while in [90], in addition to the recovery process, optimization of the acquisition process is also explored.…”

Section: Super-resolutionmentioning

confidence: 99%

Survey of Deep-Learning Approaches for Remote Sensing Observation Enhancement

Tsagkatakis

Aidini

Fotiadou

et al. 2019

Sensors

111

View full text Add to dashboard Cite

Deep Learning, and Deep Neural Networks in particular, have established themselves as the new norm in signal and data processing, achieving state-of-the-art performance in image, audio, and natural language understanding. In remote sensing, a large body of research has been devoted to the application of deep learning for typical supervised learning tasks such as classification. Less yet equally important effort has also been allocated to addressing the challenges associated with the enhancement of low-quality observations from remote sensing platforms. Addressing such channels is of paramount importance, both in itself, since high-altitude imaging, environmental conditions, and imaging systems trade-offs lead to low-quality observation, as well as to facilitate subsequent analysis, such as classification and detection. In this paper, we provide a comprehensive review of deep-learning methods for the enhancement of remote sensing observations, focusing on critical tasks including single and multi-band super-resolution, denoising, restoration, pan-sharpening, and fusion, among others. In addition to the detailed analysis and comparison of recently presented approaches, different research avenues which could be explored in the future are also discussed.

show abstract

HSCNN: CNN-Based Hyperspectral Image Recovery from Spectrally Undersampled Projections

Cited by 190 publications

References 25 publications

Optimized Multi-Spectral Filter Arrays for Spectral Reconstruction

Optimized Multi-Spectral Filter Arrays for Spectral Reconstruction

Multispectral Image Reconstruction From Color Images Using Enhanced Variational Autoencoder and Generative Adversarial Network

Survey of Deep-Learning Approaches for Remote Sensing Observation Enhancement

Contact Info

Product

Resources

About