Reconstruction of Hyperspectral Data From RGB Images With Prior Category Information

Yan, Longbin; Wang, Xiuheng; Zhao, Min; Kaloorazi, Maboud F.; Chen, Jie; Rahardja, Susanto

doi:10.1109/tci.2020.3000320

Cited by 47 publications

(20 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method is similar to recent spectral resolution enhancement methods [43,44] that focus on learning the spectral mapping between MSIs and HSIs. However, the methods for spectral resolution enhancement are usually supervised training methods [45,46], which learn the spectral mapping from plentiful MSI and HSI pairs that are collected in other observed scenes. In contrast, in the HR MSI and LR HSI fusion task, the HR MSI and LR HSI are captured in the same observed scene.…”

Section: Problem Formulationmentioning

confidence: 99%

Hyperspectral Image Super-Resolution with Self-Supervised Spectral-Spatial Residual Network

Chen

Zheng

2021

Remote Sensing

View full text Add to dashboard Cite

Recently, many convolutional networks have been built to fuse a low spatial resolution (LR) hyperspectral image (HSI) and a high spatial resolution (HR) multispectral image (MSI) to obtain HR HSIs. However, most deep learning-based methods are supervised methods, which require sufficient HR HSIs for supervised training. Collecting plenty of HR HSIs is laborious and time-consuming. In this paper, a self-supervised spectral-spatial residual network (SSRN) is proposed to alleviate dependence on a mass of HR HSIs. In SSRN, the fusion of HR MSIs and LR HSIs is considered a pixel-wise spectral mapping problem. Firstly, this paper assumes that the spectral mapping between HR MSIs and HR HSIs can be approximated by the spectral mapping between LR MSIs (derived from HR MSIs) and LR HSIs. Secondly, the spectral mapping between LR MSIs and LR HSIs is explored by SSRN. Finally, a self-supervised fine-tuning strategy is proposed to transfer the learned spectral mapping to generate HR HSIs. SSRN does not require HR HSIs as the supervised information in training. Simulated and real hyperspectral databases are utilized to verify the performance of SSRN.

show abstract

Section: Problem Formulationmentioning

confidence: 99%

Hyperspectral Image Super-Resolution with Self-Supervised Spectral-Spatial Residual Network

Chen

Zheng

2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Many methods generate HSI from RGB images in natural scene. Some methods use image priors such as Yan et al introduce category and location information into the network [48]. In [49], the authors adopt dictionary learning and in [50] manifold learning is used for the HSI generating.…”

Section: B Spectral Super-resolutionmentioning

confidence: 99%

“…• RMSE (Root Mean Squared Error) measures the pixelwise square root error between spectra generated and the real. It is the most commonly used metric in RGB-to-HSI research [19,28,30,48,49,[51][52][53][54][55][56][57][58].…”

Section: (I)mentioning

confidence: 99%

See 1 more Smart Citation

Hyperspectral Remote Sensing Imagery Generation From RGB Images Based on Joint Discrimination

Liu

Lei

Shi

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…We show that our method accurately and robustly detects spoofs without any spoof supervision or fine-tuning with spoof examples. Following the previous studies on hyperspectral image analysis, HSIs of vegetables and fruits were used for the evaluation [13,14,15]. The spoofs in the test images include print, replay, and fake attacks.…”

Section: Introductionmentioning

confidence: 99%

A Hyperspectral Approach For Unsupervised Spoof Detection With Intra-Sample Distribution

Kaichi

Ozasa

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Despite the high recognition accuracy of recent deep neural networks, they can be easily deceived by spoofing. Spoofs (e.g., a printed photograph) visually resemble the actual objects quite closely. Thus, we propose a method for spoof detection with a hyperspectral image (HSI) that can effectively detect differences in surface materials. In contrast to existing anti-spoofing approaches, the proposed method learns the feature representation for spoof detection without spoof supervision. The informative pixels on an HSI are embedded onto the feature space, and we identify the spoof from their distribution. As this is the first attempt at unsupervised spoof detection with an HSI, a new dataset that includes spoofs, named Hyperspectral Spoof Dataset (HSSD), has been developed. The experimental results indicate that the proposed method performs significantly better than the baselines. The source code and the dataset are available on Github. 1

show abstract

Reconstruction of Hyperspectral Data From RGB Images With Prior Category Information

Cited by 47 publications

References 46 publications

Hyperspectral Image Super-Resolution with Self-Supervised Spectral-Spatial Residual Network

Hyperspectral Image Super-Resolution with Self-Supervised Spectral-Spatial Residual Network

Hyperspectral Remote Sensing Imagery Generation From RGB Images Based on Joint Discrimination

A Hyperspectral Approach For Unsupervised Spoof Detection With Intra-Sample Distribution

Contact Info

Product

Resources

About