@Article{cmc.2025.071397,
AUTHOR = {Jiajia Liu, Junyi Lin, Wenxiang Dong, Xuan Zhao, Jianhua Liu, Huiru Li},
TITLE = {BAID: A Lightweight Super-Resolution Network with Binary Attention-Guided Frequency-Aware Information Distillation},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {86},
YEAR = {2026},
NUMBER = {2},
PAGES = {1--19},
URL = {http://www.techscience.com/cmc/v86n2/64783},
ISSN = {1546-2226},
ABSTRACT = {Single Image Super-Resolution (SISR) seeks to reconstruct high-resolution (HR) images from low-resolution (LR) inputs, thereby enhancing visual fidelity and the perception of fine details. While Transformer-based models—such as SwinIR, Restormer, and HAT—have recently achieved impressive results in super-resolution tasks by capturing global contextual information, these methods often suffer from substantial computational and memory overhead, which limits their deployment on resource-constrained edge devices. To address these challenges, we propose a novel lightweight super-resolution network, termed Binary Attention-Guided Information Distillation (BAID), which integrates frequency-aware modeling with a binary attention mechanism to significantly reduce computational complexity and parameter count while maintaining strong reconstruction performance. The network combines a high–low frequency decoupling strategy with a local–global attention sharing mechanism, enabling efficient compression of redundant computations through binary attention guidance. At the core of the architecture lies the Attention-Guided Distillation Block (AGDB), which retains the strengths of the information distillation framework while introducing a sparse binary attention module to enhance both inference efficiency and feature representation. Extensive ×4 super-resolution experiments on four standard benchmarks—Set5, Set14, BSD100, and Urban100—demonstrate that BAID achieves Peak Signal-to-Noise Ratio (PSNR) values of 32.13, 28.51, 27.47, and 26.15, respectively, with only 1.22 million parameters and 26.1 G Floating-Point Operations (FLOPs), outperforming other state-of-the-art lightweight methods such as Information Multi-Distillation Network (IMDN) and Residual Feature Distillation Network (RFDN). These results highlight the proposed model’s ability to deliver high-quality image reconstruction while offering strong deployment efficiency, making it well-suited for image restoration tasks in resource-limited environments.},
DOI = {10.32604/cmc.2025.071397}
}