Advancing Image Super-resolution Techniques in Remote Sensing: A Comprehensive Survey

2025-05-29

AI Summary

Existing remote sensing image super-resolution (RSISR) surveys lack systematicity, and mainstream methods struggle to simultaneously preserve fine-grained texture fidelity and geometric structural integrity under large-scale degradations. To address this, we propose the first three-dimensional taxonomy—spanning methodologies, datasets, and evaluation protocols—to systematically categorize supervised and unsupervised paradigms, benchmark datasets, and quantitative metrics, thereby exposing the performance gap between synthetically degraded and real-world scenarios. Through comprehensive literature analysis and cross-paradigm comparison, we identify recurrent bottlenecks: texture distortion and structural deformation. Building on these insights, we formulate RSISR-specific architectural design principles and a robust evaluation protocol. Our work delivers reproducible benchmarking recommendations and a technology roadmap, establishing a foundation for the practical advancement of RSISR.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Remote sensing image super-resolution (RSISR) is a crucial task in remote sensing image processing, aiming to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts. Despite the growing number of RSISR methods proposed in recent years, a systematic and comprehensive review of these methods is still lacking. This paper presents a thorough review of RSISR algorithms, covering methodologies, datasets, and evaluation metrics. We provide an in-depth analysis of RSISR methods, categorizing them into supervised, unsupervised, and quality evaluation approaches, to help researchers understand current trends and challenges. Our review also discusses the strengths, limitations, and inherent challenges of these techniques. Notably, our analysis reveals significant limitations in existing methods, particularly in preserving fine-grained textures and geometric structures under large-scale degradation. Based on these findings, we outline future research directions, highlighting the need for domain-specific architectures and robust evaluation protocols to bridge the gap between synthetic and real-world RSISR scenarios.

Problem

• Reviewing RSISR methods to understand trends and challenges
• Analyzing limitations in preserving textures and structures
• Proposing future directions for domain-specific architectures

Innovation

• Comprehensive review of RSISR algorithms
• Categorizes methods into supervised and unsupervised
• Highlights need for domain-specific architectures