Statistics of real-world hyperspectral images

By Ayan Chakrabarti, Todd Zickler. Computer Vision and Pattern Recognition, 2011

613 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/cac28d264e0cf9a62f2511481a6a6235bf985afe

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Leyuan Fang
2. Lei Zhang
3. Shutao Li
4. Renwei Dian
5. Luc Van Gool
6. Wangmeng Zuo
7. Ming-Hsuan Yang
8. Dacheng Tao

In Media Technology

1. Leyuan Fang
2. Renwei Dian
3. Shutao Li
4. Guangming Shi
5. Weisheng Dong
6. Konrad Schindler
7. Emmanuel Baltsavias
8. Charis Lanaras

Citations in the corpus

• HSCNN+: Advanced CNN-Based Hyperspectral Recovery from RGB Images (2018, background): “As there is a high correlation between RGB values and their corresponding hyperspectral radiance [9], the second category of methods manage to exploit this correlation from a large number of training data and directly model the mapping between RGB and hyperspectral images.”
• Methods for image denoising using convolutional neural network: a review (2021, background): “…MIT-Adobe five k [128], ImageNet [129], BSD68 [130], Set 14 [131], Renoir [132], NC12 [133], NAM [134], SIDD [135], SUN397 [136], Set5 [137], CAVE [138],Harvard database [139], MRI brain dataset [140], LIVE1, Chelsea,DIV2K dataset [141], HIS dataset Xiongan, first Affiliated Hospital of Sun…”
• Hyperspectral Image Super-Resolution via Non-local Sparse Tensor Factorization (2017, methodology): “In this section, experiments are conducted on two public databases (CAVE database [37](1) and Harvard database [8](2)) to evaluate the effectiveness of the proposed NLSTF method.”
• Sparse Recovery of Hyperspectral Signal from Natural RGB Images (2016, methodology): “Finally, we applied our approach to the hyperspectral database acquired by Chakrabarti and Zickler [27].”
• Bayesian sparse representation for hyperspectral image super resolution (2015, methodology): “(Right) ‘Img 1’ form the Harvard database [9].”
• Hyperspectral Image Super-Resolution via Non-Negative Structured Sparse Representation (2016, methodology): “The HR RGB images from the CAVE (the first row) [31] and Harvard (the second row) [32] TABLE I THE AVERAGE AND STANDARD DEVIATION OF PSNR, RMSE, SAM, AND ERGAS RESULTS OF THE TEST METHODS FOR DIFFERENT SCALING FACTORS ON THE CAVE DATASET [31] method are set as follows: the number of atoms in diction”
• Hyperspectral Super-Resolution by Coupled Spectral Unmixing (2015, background): “Example image from the Harvard database.”
• Color Constancy by Learning to Predict Chromaticity from Luminance (2015, result): “This is consistent with findings that reflectance functions are usually smooth (PCA on pixel spectra in [17] revealed a Fourier-like basis).”