HIMOSA: Efficient Remote Sensing Image Super-Resolution with Hierarchical Mixture of Sparse Attention

2025-11-28

AI Summary

Addressing the trade-off between model performance and computational efficiency in remote sensing image super-resolution, this paper proposes a lightweight network framework. The method introduces three key innovations: (1) a content-aware sparse attention mechanism that dynamically focuses on salient regions to model long-range dependencies; (2) a hierarchical window expansion strategy that adaptively adjusts sparsity to efficiently capture multi-scale repetitive patterns; and (3) a hybrid design integrating lightweight convolutions with dynamic computation optimization modules. The proposed approach achieves high reconstruction fidelity while significantly reducing FLOPs and parameter count. Extensive experiments demonstrate state-of-the-art performance across multiple remote sensing benchmarks, with 2.1–3.4× faster inference speed compared to existing methods. The framework exhibits strong real-time capability and high suitability for edge deployment.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Learning on the Edge & Model Compression
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

In remote sensing applications, such as disaster detection and response, real-time efficiency and model lightweighting are of critical importance. Consequently, existing remote sensing image super-resolution methods often face a trade-off between model performance and computational efficiency. In this paper, we propose a lightweight super-resolution framework for remote sensing imagery, named HIMOSA. Specifically, HIMOSA leverages the inherent redundancy in remote sensing imagery and introduces a content-aware sparse attention mechanism, enabling the model to achieve fast inference while maintaining strong reconstruction performance. Furthermore, to effectively leverage the multi-scale repetitive patterns found in remote sensing imagery, we introduce a hierarchical window expansion and reduce the computational complexity by adjusting the sparsity of the attention. Extensive experiments on multiple remote sensing datasets demonstrate that our method achieves state-of-the-art performance while maintaining computational efficiency.

Problem

• Balancing model performance and computational efficiency in remote sensing image super-resolution
• Reducing computational complexity while maintaining strong reconstruction performance
• Leveraging multi-scale repetitive patterns in remote sensing imagery for efficient super-resolution

Innovation

• Hierarchical mixture of sparse attention mechanism
• Content-aware sparse attention for fast inference
• Hierarchical window expansion reduces computational complexity