Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution

被引:190
|
作者
Qu, Ying [1 ]
Qi, Hairong [1 ]
Kwan, Chiman [2 ]
机构
[1] Univ Tennessee, Knoxville, TN 37996 USA
[2] Appl Res LLC, Rockville, MD USA
来源
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2018年
关键词
MULTISPECTRAL DATA; CLASSIFICATION; RESOLUTION; FUSION;
D O I
10.1109/CVPR.2018.00266
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In many computer vision applications, obtaining images of high resolution in both the spatial and spectral domains are equally important. However, due to hardware limitations, one can only expect to acquire images of high resolution in either the spatial or spectral domains. This paper focuses on hyperspectral image super-resolution (HSI-SR), where a hyperspectral image (HSI) with low spatial resolution (LR) but high spectral resolution is fused with a multispectral image (MSI) with high spatial resolution (HR) but low spectral resolution to obtain HR HSI. Existing deep learning-based solutions are all supervised that would need a large training set and the availability of HR HSI, which is unrealistic. Here, we make the first attempt to solving the HSI-SR problem using an unsupervised encoder-decoder architecture that carries the following uniquenesses. First, it is composed of two encoder-decoder networks, coupled through a shared decoder, in order to preserve the rich spectral information from the HSI network. Second, the network encourages the representations from both modalities to follow a sparse Dirichlet distribution which naturally incorporates the two physical constraints of HSI and MSI. Third, the angular difference between representations are minimized in order to reduce the spectral distortion. We refer to the proposed architecture as unsupervised Sparse Dirichlet-Net, or uSDN. Extensive experimental results demonstrate the superior performance of uSDN as compared to the state-of-the-art.
引用
收藏
页码:2511 / 2520
页数:10
相关论文
共 50 条
  • [1] Unsupervised and Unregistered Hyperspectral Image Super-Resolution With Mutual Dirichlet-Net
    Qu, Ying
    Qi, Hairong
    Kwan, Chiman
    Yokoya, Naoto
    Chanussot, Jocelyn
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [2] UTDN: AN UNSUPERVISED TWO-STREAM DIRICHLET-NET FOR HYPERSPECTRAL UNMIXING
    Jin, Qiwen
    Ma, Yong
    Mei, Xiaoguang
    Li, Hao
    Ma, Jiayi
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 1885 - 1889
  • [3] Enhanced Deep Image Prior for Unsupervised Hyperspectral Image Super-Resolution
    Li, Jiaxin
    Zheng, Ke
    Gao, Lianru
    Han, Zhu
    Li, Zhi
    Chanussot, Jocelyn
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2025, 63
  • [4] A Spectral Diffusion Prior for Unsupervised Hyperspectral Image Super-Resolution
    Liu, Jianjun
    Wu, Zebin
    Xiao, Liang
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
  • [5] UNSUPERVISED GENERATIVE NETWORK FOR BLIND HYPERSPECTRAL IMAGE SUPER-RESOLUTION
    Liu, Zhe
    Han, Xian-Hua
    Sun, Jiande
    Chen, Yen-Wei
    2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2022, : 2621 - 2625
  • [6] Model Inspired Autoencoder for Unsupervised Hyperspectral Image Super-Resolution
    Liu, Jianjun
    Wu, Zebin
    Xiao, Liang
    Wu, Xiao-Jun
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [7] Adaptive Nonnegative Sparse Representation for Hyperspectral Image Super-Resolution
    Li, Xuesong
    Zhang, Youqiang
    Ge, Zixian
    Cao, Guo
    Shi, Hao
    Fu, Peng
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 : 4267 - 4283
  • [8] Sparse Spatio-spectral Representation for Hyperspectral Image Super-resolution
    Akhtar, Naveed
    Shafait, Faisal
    Mian, Ajmal
    COMPUTER VISION - ECCV 2014, PT VII, 2014, 8695 : 63 - 78
  • [9] Nonlocal Patch Tensor Sparse Representation for Hyperspectral Image Super-Resolution
    Xu, Yang
    Wu, Zebin
    Chanussot, Jocelyn
    Wei, Zhihui
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (06) : 3034 - 3047
  • [10] LOCAL SIMILARITY REGULARIZED SPARSE REPRESENTATION FOR HYPERSPECTRAL IMAGE SUPER-RESOLUTION
    Tang, Songze
    Zhou, Nan
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 5120 - 5123