Single image super-resolution (SISR) plays a crucial role in enhancing image quality for resource-constrained devices, particularly in biomedical imaging and point-of-care diagnostics. However, existing SISR methods face a fundamental trade-off: high-performance models achieve excellent reconstruction quality but require substantial computational resources, while lightweight approaches significantly reduce complexity at the cost of notable performance degradation. To address this challenge, this paper proposes HOLI-SRNet, a unified lightweight SISR framework specifically designed for resource-constrained deployment. The framework integrates three synergistic components: (1) COMPASS—a comprehensive pruning and sparsification strategy that reduces parameter redundancy through hybrid structured/unstructured pruning while preserving essential features; (2) dual-attention mechanisms—attention-based adaptive residual block (AARB) for dynamic kernel selection and Attention-based cross-layer connection (ACC) for adaptive multi-scale feature fusion; (3) hardware–software co-optimization—specialized operator libraries and intelligent scheduling mechanisms that bridge the gap between algorithmic efficiency and hardware-specific acceleration. Experimental results demonstrate HOLI-SRNet’s effectiveness in balancing performance and efficiency: the framework achieves competitive reconstruction quality (32.29dB PSNR) while requiring 96% fewer parameters than EDSR (1.7M vs 43.1M), delivers 20% faster inference than DEM-SRNet at small batch sizes, and provides 80% higher throughput with 50.8% lower latency than BRNN models. Practical deployment validation on three resource-constrained devices confirms the framework’s cross-platform compatibility and real-time processing capabilities.HOLI-SRNet enables practical SISR deployment in critical applications including portable medical devices for real-time image enhancement, mobile microscopy systems requiring improved specimen resolution, and edge computing environments where both memory and computational resources are limited, providing a viable solution for high-quality image processing on resource-constrained platforms.
Ju et al. (Sat,) studied this question.