MTSR-GAN: A Progressive Residual GAN Structure Combined With the Swin-Transformer for Multitask Cross-Sensor Satellite Image Super-Resolution

In recent years, super-resolution (SR) reconstruction techniques for remote sensing imagery has attracted extensive attention due to its advantages of a low cost and flexible and convenient application. Unlike conventional SR tasks, the SR reconstruction of remote sensing images under real-world conditions is usually accompanied by a large number of objective unfavorable factors, including high levels of noise, cloud occlusion, and variability across different sensors. Consequently, real-scene SR reconstruction constitutes a multitask problem, yet existing SR approaches seldom address these challenges in a unified framework. To overcome these limitations, this study proposes a multitask SR reconstruction network named multitask SR reconstruction generative adversarial network (GAN) specifically designed for real-world remote sensing imagery. The proposed network adopts the GAN model’s structure, and integrates three dedicated modules within the generator: a deep feature extraction module, a spectral transfer module, and a thin cloud removal module. Within this framework, we design a novel Swin Transformer module to enhance spatial diversity and training stability in image reconstruction. Moreover, we introduce a framework termed the efficient feature aggregation architecture, which ensures effective feature fusion while enabling seamless collaboration among these components. Together, these components enable effective adaptation to cross-sensor SR reconstruction tasks under complex real-world conditions. The proposed method is verified by both quantitative and qualitative analyses. The SR reconstruction results obtained on multiple datasets show that the proposed method is superior to the existing mainstream methods.

• Publication year

  2026

• Venue

  IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

• Publication date

  Unknown publication date

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1109/JSTARS.2025.3631332
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• MambaHSISR: Mamba Hyperspectral Image Super-Resolution

  2025cited by this paper
• Discrimination of Larch Needle Pest Severity Based on Sentinel-2 Super-Resolution and Spectral Derivatives—A Case Study of Erannis jacobsoni Djak

  2025cited by this paper
• Improving the Spatial Resolution of Small Satellites by Implementing a Super-Resolution Algorithm Based on the Optical Imaging Sensor’s Rotation Approach

  2024cited by this paper
• Frequency-Assisted Mamba for Remote Sensing Image Super-Resolution

  2024cited by this paper
• CasFormer: Cascaded transformers for fusion-aware computational hyperspectral imaging

  2024cited by this paper
• Quantifying trade-offs in satellite hardware configurations using a super-resolution framework with realistic image degradation

  2024cited by this paper
• SonarNet: Hybrid CNN-Transformer-HOG Framework and Multifeature Fusion Mechanism for Forward-Looking Sonar Image Segmentation

  2024cited by this paper
• YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

  2024cited by this paper
• Multilevel Class Token Transformer With Cross TokenMixer for Hyperspectral Images Classification

  2024cited by this paper
• High-Resolution Methane Mapping With the EnMAP Satellite Imaging Spectroscopy Mission

  2024cited by this paper
• MambaIRv2: Attentive State Space Restoration

  2024influential reference
• Very fine spatial resolution urban land cover mapping using an explicable sub-pixel mapping network based on learnable spatial correlation

  2023cited by this paper
• ConvNets Match Vision Transformers at Scale

  2023cited by this paper
• Global urban high-resolution land-use mapping: From benchmarks to multi-megacity applications

  2023cited by this paper
• Transformer-Based Fused Attention Combined with CNNs for Image Classification

  2023cited by this paper
• Transformer for object detection: Review and benchmark

  2023cited by this paper
• DBCT-Net:A dual branch hybrid CNN-transformer network for remote sensing image fusion

  2023cited by this paper
• LRR-Net: An Interpretable Deep Unfolding Network for Hyperspectral Anomaly Detection

  2023cited by this paper
• SUNet: Swin Transformer UNet for Image Denoising

  2022influential reference
• A Review of Image Super-Resolution Approaches Based on Deep Learning and Applications in Remote Sensing

  2022cited by this paper
• Swin Transformer Embedding UNet for Remote Sensing Image Semantic Segmentation

  2022cited by this paper
• Collaborative Network for Super-Resolution and Semantic Segmentation of Remote Sensing Images

  2022cited by this paper
• SwinIR: Image Restoration Using Swin Transformer

  2021influential reference
• CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

  2021cited by this paper
• CogView: Mastering Text-to-Image Generation via Transformers

  2021cited by this paper
• TrSeg: Transformer for semantic segmentation

  2021cited by this paper
• CMT: Convolutional Neural Networks Meet Vision Transformers

  2021cited by this paper
• nnFormer: Volumetric Medical Image Segmentation via a 3D Transformer

  2021cited by this paper
• A Review of Spatiotemporal Super-Resolution Mapping for Remote Sensing Data Fusion

  2021cited by this paper
• STransFuse: Fusing Swin Transformer and Convolutional Neural Network for Remote Sensing Image Semantic Segmentation

  2021cited by this paper
• Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction

  2021cited by this paper
• General Multi-label Image Classification with Transformers

  2020cited by this paper
• Correction to: Single Image Super-Resolution via a Holistic Attention Network

  2020influential reference
• RUNet: A Robust UNet Architecture for Image Super-Resolution

  2019cited by this paper
• Cloud removal in remote sensing images using nonnegative matrix factorization and error correction

  2019cited by this paper
• Image Super-Resolution Using Very Deep Residual Channel Attention Networks

  2018influential reference
• A Tutorial on Sparse Signal Reconstruction and Its Applications in Signal Processing

  2018cited by this paper
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

  2018influential reference
• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

  2017influential reference
• Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources

  2017cited by this paper
• Perspective of Chinese GF-1 high-resolution satellite data in agricultural remote sensing monitoring

  2017cited by this paper
• Satellite Remote Sensing: Sensors, Applications and Techniques

  2017cited by this paper
• Improved Training of Wasserstein GANs

  2017cited by this paper
• Updating Landsat-based forest cover maps with MODIS images using multiscale spectral-spatial-temporal superresolution mapping

  2017cited by this paper
• High-resolution mapping of global surface water and its long-term changes

  2016cited by this paper
• Remote Sensing Image Stripe Noise Removal: From Image Decomposition Perspective

  2016cited by this paper
• Thin Cloud Removal Based on Signal Transmission Principles and Spectral Mixture Analysis

  2016cited by this paper
• Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

  2016cited by this paper
• A Review of Quality Metrics for Fused Image

  2015cited by this paper
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014cited by this paper
• Cloud removal for remotely sensed images by similar pixel replacement guided with a spatio-temporal MRF model

  2014cited by this paper
• A review of regional science applications of satellite remote sensing in urban settings

  2013cited by this paper
• The application of small unmanned aerial systems for precision agriculture: a review

  2012cited by this paper
• Canopy-cover thematic-map generation for Military Map products using remote sensing data in inaccessible areas

  2011cited by this paper
• Image Quality Metrics: PSNR vs. SSIM

  2010cited by this paper

• No citing papers are available for this paper.