Filters








17,879 Hits in 3.6 sec

Learned Spectral Super-Resolution [article]

Silvano Galliani, Charis Lanaras, Dimitrios Marmanis, Emmanuel Baltsavias, Konrad Schindler
2017 arXiv   pre-print
We describe a novel method for blind, single-image spectral super-resolution.  ...  We demonstrate spectral super-resolution both for conventional RGB images and for multi-spectral satellite data, outperforming the state-of-the-art.  ...  The topic of this paper is single-image spectral super-resolution.  ... 
arXiv:1703.09470v1 fatcat:yf4kpi5pknesxdjlfuq7bw6ca4

Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery [article]

Junjun Jiang, He Sun, Xianming Liu, Jiayi Ma
2020 arXiv   pre-print
image super-resolution, referred as SSPSR.  ...  Recently, single gray/RGB image super-resolution reconstruction task has been extensively studied and made significant progress by leveraging the advanced machine learning techniques based on deep convolutional  ...  To exploit the abundant spectral correlations among successive spectral bands, several single hyperspectral image super-resolution approaches based on sparse and dictionary learning or low-rank approximation  ... 
arXiv:2005.08752v1 fatcat:pt3whdmj2fanpckezab6gf2xru

LSTNet: A Reference-Based Learning Spectral Transformer Network for Spectral Super-Resolution

Debao Yuan, Ling Wu, Huinan Jiang, Bingrui Zhang, Jian Li
2022 Sensors  
Spectral super-resolution (SSR) is a method that involves learning the relationship between a multispectral image (MSI) and an HSI, based on the overlap region, followed by reconstruction of the HSI by  ...  To address this problem, a novel learning spectral transformer network (LSTNet) is proposed in this paper, utilizing a reference-based learning strategy to transfer the spectral structure knowledge of  ...  A novel learning spectral transformer network (LSTNet) for SSR is proposed, which introduces the transformer architecture into the spectral super-resolution problem.  ... 
doi:10.3390/s22051978 pmid:35271131 pmcid:PMC8914896 fatcat:sqgidsrk4bhqvfmbmlswgicrja

Spectral recovery‐guided hyperspectral super‐resolution using transfer learning

Shaolei Zhang, Guangyuan Fu, Hongqiao Wang, Yuqing Zhao
2021 IET Image Processing  
Instead of directly applying the learned knowledge from the colour image domain to HSI SR, the spectral down-sampled image is fed into a spatial SR model to obtain a high-resolution image, which acts as  ...  Single hyperspectral image (HSI) super-resolution (SR) has attracted researcher's attention; however, most existing methods directly model the mapping between low-and highresolution images from an external  ...  CONCLUSIONS Here, a novel general method based on transfer learning is proposed for HSI super-resolution (SR).  ... 
doi:10.1049/ipr2.12253 fatcat:66ed4ip5i5fr3l2wm6qxbppksi

Hyperspectral Imagery Super-Resolution by Compressive Sensing Inspired Dictionary Learning and Spatial-Spectral Regularization

Wei Huang, Liang Xiao, Hongyi Liu, Zhihui Wei
2015 Sensors  
This paper proposes a novel hyperspectral imagery super-resolution (HSI-SR) method via dictionary learning and spatial-spectral regularization. The main contributions of this paper are twofold.  ...  Super-resolution (SR) imagery aims at inferring high quality images of a given scene from degraded versions of the same scene.  ...  To improve the image spatial resolution, the super-resolution (SR) technique is employed, which was firstly proposed by Tsai and Huang [2] .  ... 
doi:10.3390/s150102041 pmid:25608212 pmcid:PMC4327116 fatcat:ef73j72is5bqdocfrrimc6z7ji

DEEP RESIDUAL LEARNING FOR SINGLE-IMAGE SUPER-RESOLUTION OF MULTI-SPECTRAL SATELLITE IMAGERY

L. Wagner, L. Liebel, M. Körner
2019 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In particular, single-image super-resolution (SISR) approaches aim to achieve this goal solely by observing the individual images.  ...  As a result, this method is able to increase the perceived resolution of the 20 m channels and mesh all spectral bands.  ...  Super-resolution based on machine learning provides a better solution, as the relationship between LR and HR images is explicitly learned.  ... 
doi:10.5194/isprs-annals-iv-2-w7-189-2019 fatcat:hfpxqb4dzjcxlh6b5xxapvoz2u

Learning Spectral and Spatial Features Based on Generative Adversarial Network for Hyperspectral Image Super-Resolution

Ruituo Jiang, Xu Li, Ang Gao, Lixin Li, Hongying Meng, Shigang Yue, Lei Zhang
2019 IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium  
Super-resolution (SR) of hyperspectral images (HSIs) aims to enhance the spatial/spectral resolution of hyperspectral imagery and the super-resolved results will benefit many remote sensing applications  ...  Specifically, HSRGAN constructs spectral and spatial blocks with residual network in generator to effectively learn spectral and spatial features from HSIs.  ...  CONCLUSION This paper presents a novel super-resolution method for hyperspectral images which considers learning both spectral and spatial features based on generative adversarial network.  ... 
doi:10.1109/igarss.2019.8900228 dblp:conf/igarss/JiangLGLMYZ19 fatcat:tzsb6osp25bktnvn5mawswjsza

Learning Based Super Resolution Application for Hyperspectral Images

Hüseyin AYDİLEK, Nihat İNANÇ
2021 International scientific and vocational studies journal  
Later, the super-resolution image obtained, and the original low-spatial-resolution hyperspectral image are fused with the dictionary learning method, resulting in a new super-resolution image with high  ...  resolution and spectral resolution.  ...  The convolutional neural network model learns an end-to-end spectral difference mapping between low spatial resolution hyperspectral image and super-resolution hyperspectral image.  ... 
doi:10.47897/bilmes.1049338 fatcat:wayekvbxkngn7mn4yhwxvocpqi

Multi-modal Spectral Image Super-Resolution [chapter]

Fayez Lahoud, Ruofan Zhou, Sabine Süsstrunk
2019 Lecture Notes in Computer Science  
By combining both modalities, we build a pipeline that learns to super-resolve using multi-scale spectral inputs guided by a color image.  ...  In this paper, we tackle the problem of multi-modal spectral image super-resolution while constraining ourselves to a small dataset.  ...  Then we train residual learning networks for spectral image super-resolution.  ... 
doi:10.1007/978-3-030-11021-5_3 fatcat:mah5rje3jne57advb7elzf3z7m

Spectral Super-resolution for RGB Images using Class-based BP Neural Networks

Xiaolin Han, Jing Yu, Jing-Hao Xue, Weidong Sun
2018 2018 Digital Image Computing: Techniques and Applications (DICTA)  
This paper aims to construct a high-spatial-resolution hyperspectral (HHS) image from a highspatial-resolution RGB image, by proposing a novel class-based spectral super-resolution method.  ...  Comparisons on three standard datasets, ICVL, CAVE and NUS, demonstrate that, our proposed method achieves a better spectral super-resolution quality than related state-of-the-art methods.  ...  Spectral super-resolution methods can be mainly divided into two groups: dictionary learning based and neural network based methods. Among the dictionary learning based methods, Arad et al.  ... 
doi:10.1109/dicta.2018.8615862 dblp:conf/dicta/HanYXS18 fatcat:eygaifhaabgszb7tnql7ybplyu

Bidirectional 3D Quasi-Recurrent Neural Networkfor Hyperspectral Image Super-Resolution

Ying Fu, Zhiyuan Liang, Shaodi You
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Recently, deep learning-based methods for HSI spatial super-resolution have been actively exploited.  ...  It can only produce low spatial resolution images in most cases and thus hyperspectral image (HSI) spatial super-resolution is important.  ...  Deep Learning-Based Methods Here, we introduce three kinds of deep learning-based methods; they are RGB image super-resolution methods, HSI super-resolution methods with 2D convolution, and HSI superresolution  ... 
doi:10.1109/jstars.2021.3057936 fatcat:522lja4s65bbhhcm62lrelueby

High-throughput molecular imaging via deep learning enabled Raman spectroscopy [article]

Conor C. Horgan, Magnus Jensen, Anika Nagelkerke, Jean-Phillipe St-Pierre, Tom Vercauteren, Molly M. Stevens, Mads S. Bergholt
2020 arXiv   pre-print
Next, we develop a neural network for robust 2-4x super-resolution of hyperspectral Raman images that preserves molecular cellular information.  ...  Finally, transfer learning is applied to extend DeepeR from cell to tissue-scale imaging.  ...  Figure 3 | 3 Deep learning enabled hyperspectral image super-resolution.  ... 
arXiv:2009.13318v1 fatcat:vgmug6rbsrdwtbvgywe4mt4rpy

Hyperspectral Image Super-Resolution With Optimized RGB Guidance

Ying Fu, Tao Zhang, Yinqiang Zheng, Debing Zhang, Hua Huang
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
RGB camera on super-resolution accuracy has rarely been investigated.  ...  Previous methods for this fusion task usually employ hand-crafted priors to model the underlying structure of the latent high resolution HSI, and the effect of the camera spectral response (CSR) of the  ...  Then, we introduce our CNN-based method for the HSI super-resolution, which can effectively learn the internal recurrence of spectral information and guarantee spatial consistency.  ... 
doi:10.1109/cvpr.2019.01193 dblp:conf/cvpr/FuZZZ019 fatcat:zbmb5ssbuvcnta355zh45n5rwu

Deep Residual Convolutional Neural Network for Hyperspectral Image Super-Resolution [chapter]

Chen Wang, Yun Liu, Xiao Bai, Wenzhong Tang, Peng Lei, Jun Zhou
2017 Lecture Notes in Computer Science  
The super-resolution is achieved by minimizing the difference between the estimated image and the ground truth high resolution image.  ...  In experiments on two public datasets we show that the proposed network delivers improved hyperspectral super-resolution result than several state-of-the-art methods.  ...  Related Work In this section, we review relevant hyperspectral image super-resolution methods and deep learning methods for grayscale image super-resolution.  ... 
doi:10.1007/978-3-319-71598-8_33 fatcat:kgebxf3rwrdjpeir7f5rdffyl4

PIRM2018 Challenge on Spectral Image Super-Resolution: Methods and Results [chapter]

Mehrdad Shoeiby, Antonio Robles-Kelly, Radu Timofte, Ruofan Zhou, Fayez Lahoud, Sabine Süsstrunk, Zhiwei Xiong, Zhan Shi, Chang Chen, Dong Liu, Zheng-Jun Zha, Feng Wu (+9 others)
2019 Lecture Notes in Computer Science  
The challenge is one of the first of its kind, aiming at leveraging modern machine learning techniques to achieve spectral image super-resolution. It comprises of two tracks.  ...  The first of these (Track 1) is about example-based single spectral image super-resolution. The second one (Track 2) is on colour-guided spectral image super-resolution.  ...  Contact email: kaixuan_ wei@ outlook. com Spectral SR Members: Koushik Nagasubramanian, Asheesh K.  ... 
doi:10.1007/978-3-030-11021-5_22 fatcat:2l64hl3bmffw5b7vyb26tv624m
« Previous Showing results 1 — 15 out of 17,879 results