Ultra-lightweight semantic-injected imagery super-resolution for real-time UAV remote sensing

Abstract Real-time 2D imagery super-resolution (SR) in UAV remote sensing encounters significant speed and resource-consuming bottlenecks during large-scale processing. To overcome this, we propose semantic injection state modeling for SR, an ultra-lightweight architecture that integrates land-cover semantics into a linear state-space model. This integration mitigates state forgetting inherent in linear processing by linking hierarchical features to persistent semantic prototypes, enabling high-fidelity image enhancement. The model achieves a state-of-the-art peak signal-to-noise ratio of 32.9+ for 4x SR on RSSCN7 agricultural grassland imagery. Furthermore, the implementation of geographically-chunked (tile-based) parallel processing simultaneously eliminates computational redundancies, yielding a 10.85 × inference speedup, a 54% memory reduction, and an 8.74 × faster training time. This breakthrough facilitates practical real-time SR deployment on UAV platforms, demonstrating strong efficacy for ecological monitoring applications by providing the detailed imagery essential for accurate analysis.