Fusformer: A Transformer-Based Fusion Network for Hyperspectral Image Super-Resolution

Article Geochemistry & Geophysics

Hyperspectral Image Super-Resolution Based on Multiscale Mixed Attention Network Fusion

Jianwen Hu et al.

Summary: This letter proposes a single hyperspectral image (HSI) super-resolution (SR) method based on network fusion. It improves spatial quality by constructing 3-D multiscale mixed attention networks (3-D-MSMANs) and fusion module.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2022)

添加到收藏夹

Article Geochemistry & Geophysics

Gradient Enhanced Dual Regression Network: Perception-Preserving Super-Resolution for Multi-Sensor Remote Sensing Imagery

Zhenzhou Zhang et al.

Summary: A new SISR algorithm named GEDRN is proposed, which improves image perceptual quality by introducing gradient information and perceptual loss; the algorithm is trained and tested on real-world multi-sensor satellite images, with experimental results demonstrating its superiority.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2022)

添加到收藏夹

Article Geochemistry & Geophysics

Spatio-Temporal Dual-Branch Network With Predictive Feature Learning for Satellite Video Object Segmentation

Yanfei Zhong et al.

Summary: This article proposes a satellite video object segmentation method based on a spatio-temporal dual-branch network. The method utilizes predictive feature learning to achieve segmentation results with temporal consistency and uses a fully convolutional network to extract spatial information for end-to-end segmentation without post-processing operations. Experimental results demonstrate that the proposed method outperforms other current SVOS models.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion

Qi Xie et al.

Summary: This paper presents a network architecture called MHF-net for multispectral and hyperspectral image fusion task. MHF-net not only has clear interpretability, but also effectively combines high-resolution multispectral and low-resolution hyperspectral images. With careful design of the model and algorithm, MHF-net demonstrates good generalization capability and outperforms state-of-the-art methods in both simulated and real data.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Hyperspectral Image Super-Resolution via Deep Spatiospectral Attention Convolutional Neural Networks

Jin-Fan Hu et al.

Summary: The paper introduces a deep convolutional neural network architecture to fuse low-resolution HSI and high-resolution multispectral image for generating high-resolution HSI. By preserving spatial and spectral information using LR-HSI and HR-MSI, and utilizing attention and pixelShuffle modules for high-quality spatial details extraction, the proposed network achieves the best performance compared to recent HSI super-resolution approaches.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Regularizing Hyperspectral and Multispectral Image Fusion by CNN Denoiser

Renwei Dian et al.

Summary: This article introduces a novel HSI and MSI fusion method, combining subspace representation and CNN denoiser, trained on gray images and directly applicable to any HSI and MSI datasets for superior performance.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Recent advances and new guidelines on hyperspectral and multispectral image fusion

Renwei Dian et al.

Summary: This paper provides a comprehensive review and categorization of hyperspectral image (HSI) and multispectral image (MSI) fusion methods, including pan-sharpening, matrix factorization, tensor representation, and deep convolution neural network. The characteristics, discussions, and comparisons of various fusion methods are introduced, along with the existing challenges and potential future directions for HSI-MSI fusion.

INFORMATION FUSION (2021)

添加到收藏夹

Article Geochemistry & Geophysics

SSR-NET: SpatialSpectral Reconstruction Network for Hyperspectral and Multispectral Image Fusion

Xueting Zhang et al.

Summary: The article proposes an interpretable spatial-spectral reconstruction network (SSR-NET) based on CNN for efficient fusion of HSI and MSI. The SSR-NET consists of three components for cross-mode message inserting, spatial reconstruction, and spectral reconstruction, achieving superior or competitive results in comparison with seven state-of-the-art methods on six HSI data sets.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2021)

添加到收藏夹

Article Geochemistry & Geophysics

Graph Convolutional Networks for Hyperspectral Image Classification

Danfeng Hong et al.

Summary: This article thoroughly investigates the applications of Convolutional Neural Networks (CNNs) and Graph Convolutional Networks (GCNs) in hyperspectral image classification. By developing a new minibatch GCN (miniGCN) to train and infer large-scale GCNs, as well as exploring fusion strategies for different types of HS features, the study achieves good classification performance.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2021)

添加到收藏夹

Article Geochemistry & Geophysics

FLOP-Reduction Through Memory Allocations Within CNN for Hyperspectral Image Classification

Mercedes E. Paoletti et al.

Summary: A new few-parameter CNN for HSI classification, based on shift operations, is introduced to reduce the number of parameters and computational complexity. The method shows promising results in terms of computational performance and classification accuracy.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Distributed Deep Learning for Remote Sensing Data Interpretation

Juan M. Haut et al.

Summary: Deep learning is a promising field for interpreting remote sensing data, especially with the increasing data quality and quantity from spaceborne and airborne platforms. However, challenges exist in terms of processing time and storage capacity due to the high dimensionality of the data.

PROCEEDINGS OF THE IEEE (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging

Tao Huang et al.

Summary: This paper proposes a novel HSI reconstruction method based on GSM prior, using deep learning DCNN to learn scale prior and estimate local means, and jointly optimizing MAP estimation algorithm and DCNN parameters through end-to-end training. Extensive experimental results demonstrate its superiority over existing methods.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence