Hierarchical Self-Attention-Based Unified Reconstruction Network for Hyperspectral Image Super-Resolution

Hyperspectral image (HSI) super-resolution aims to improve the spatial resolution of the HSI. Existing methods, particularly those based on convolutional neural networks, often suffer from limited receptive fields, which hinder their ability to capture global features within the image. The lack of global features leads to weakened results for HSI super-resolution. To address these issues, we propose a Unified Reconstruction Network (URC-Net), a deep learning framework that introduces a new self-attention mechanism to autoencoders to effectively fuse HSI and multispectral images. URC-Net improve spatial resolution by capturing global features, and the accuracy of hyperspectral image reconstruction. Extensive experiments across Pavia University datasets validate the effectiveness of our method, showing superior performance compared to existing fusion techniques.

• Publication year

  2025

• Venue

  IEEE International Geoscience and Remote Sensing Symposium

• Publication date

  2025-08-03

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/IGARSS55030.2025.11242737
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• TSSA-Net: two-stream self-attention network for hyperspectral image super-resolution

  2024cited by this paper
• DAAN: A Deep Autoencoder-Based Augmented Network for Blind Multilinear Hyperspectral Unmixing

  2024cited by this paper
• A Coarse-to-Fine Hyperspectral Target Detection Method Based on Low-Rank Tensor Decomposition

  2023cited by this paper
• ACGT-Net: Adaptive Cuckoo Refinement-Based Graph Transfer Network for Hyperspectral Image Classification

  2023cited by this paper
• Deep Unsupervised Blind Hyperspectral and Multispectral Data Fusion

  2022cited by this paper
• Learning Tensor Low-Rank Representation for Hyperspectral Anomaly Detection

  2022cited by this paper
• Physics-Based GAN With Iterative Refinement Unit for Hyperspectral and Multispectral Image Fusion

  2021cited by this paper
• Coupled Convolutional Neural Network With Adaptive Response Function Learning for Unsupervised Hyperspectral Super Resolution

  2020cited by this paper
• Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution

  2020cited by this paper
• Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution

  2018cited by this paper
• Deep Hyperspectral Image Sharpening

  2018cited by this paper
• Advances in Hyperspectral Image Classification: Earth Monitoring with Statistical Learning Methods

  2013cited by this paper
• Hyperspectral resolution enhancement using high-resolution multispectral imagery with arbitrary response functions

  2005cited by this paper
• Smoothing Filter-based Intensity Modulation: A spectral preserve image fusion technique for improving spatial details

  2000cited by this paper

• No citing papers are available for this paper.