2020
DOI: 10.1109/tci.2020.3000320
|View full text |Cite
|
Sign up to set email alerts
|

Reconstruction of Hyperspectral Data From RGB Images With Prior Category Information

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
20
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 47 publications
(20 citation statements)
references
References 46 publications
0
20
0
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%
“…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%
“…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
“…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%