Hyperspectral Image Restoration Using Low-Rank Matrix Recovery

By Hongyan Zhang, Wei He, Liangpei Zhang, Huanfeng Shen, Qiangqiang Yuan. IEEE Transactions on Geoscience and Remote Sensing, 2014

821 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/12a16464940843661b954202fb20e6fa2b6195a4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Pedram Ghamisi
2. Behnood Rasti
3. Huanfeng Shen
4. Hongyan Zhang
5. Wei He
6. Liangpei Zhang
7. Jocelyn Chanussot
8. Javier Plaza

In Computer Vision and Pattern Recognition

1. Jocelyn Chanussot
2. Antonio J. Plaza
3. Danfeng Hong
4. Pedram Ghamisi
5. Jing Yao
6. Swalpa Kumar Roy
7. Javier Plaza
8. Hongyan Zhang

In Media Technology

1. Antonio J. Plaza
2. Jocelyn Chanussot
3. Pedram Ghamisi
4. Danfeng Hong
5. Jun Yu Li
6. Javier Plaza
7. José M. Bioucas-Dias
8. Swalpa Kumar Roy

Citations in the corpus

• Noise Reduction in Hyperspectral Imagery: Overview and Application (2018, methodology): “This mixture assumption was used in [59] where HSI was denoised by solving”
• Hyperspectral Image Denoising via Tensor Low-Rank Prior and Unsupervised Deep Spatial–Spectral Prior (2022, background): “For example, Zhang et al. [21] ordered the patch of the HSI into a matrix lexicographically and proposed a low-rank matrix recovery model for HSI denoising.”
• Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art (2017, methodology): “This mixture assumption was used in [270], where low-rank and sparse matrix decomposition was taken into account to restore HSIs.”
• Total-Variation-Regularized Low-Rank Matrix Factorization for Hyperspectral Image Restoration (2016, methodology): “To thoroughly evaluate the performance of the proposed algorithm, we selected two different noise removal methods for comparison, i.e., the SSAHTV model [19] and the low-rank matrix recovery (LRMR) model [27].”
• Hyperspectral Image Denoising Employing a Spatial–Spectral Deep Residual Convolutional Neural Network (2018, neutral): “The proposed method was compared with the current mainstream methods of HSSNR [12], low-rank tensor approximation (LRTA) [18], BM4D [15], and LRMR [19].”
• Hyperspectral Image Classification—Traditional to Deep Models: A Survey for Future Prospects (2021, background): “Thus, considering the aforementioned limitations, HSI analysis is categorized into the following main streams: dimensionality reduction [6]–[8], spectral unmixing [9]–[14], change detection [15]–[17] classification [18]–[21], feature learning for classification [22]–[24], restoration and denoising [”
• Kronecker-Basis-Representation Based Tensor Sparsity and Its Applications to Tensor Recovery (2018, neutral): “A more general noise assumption utilized to model the RPCA problem is to consider the noise as a mixture of sparse noise and Gaussian noise [72].”