Lightweight Remote-Sensing Image Super-Resolution via Attention-Based Multilevel Feature Fusion Network

In recent years, advancements in remote-sensing image super-resolution (RSISR) have achieved remarkable performance. However, many methods demand significant computational resources. This is problematic for edge devices with limited computational capabilities. To alleviate this problem, we propose an attention-based multilevel feature fusion network (AMFFN) to enhance the resolution of RSIs. This proposed network integrates three efficient design strategies to provide a lightweight solution. Initially, we designed the partial shallow residual block (PSRB) to replace the redundant convolution operation. The PSRB optimizes feature extraction via partial convolution (PConv) and capitalizes on information across channels using pointwise convolution (PWConv). Subsequently, integrating the PSRB, our dynamic feature distillation block (DFDB) leverages an information distillation mechanism to distill and capture only the crucial features securing a robust feature depiction. Conclusively, for superior feature fusion, we conceptualized an attention-based multilevel feature fusion (AMFF) mechanism. The attention intrinsic to AMFF weighs the significance of features from varied branches, assuring that the resulting output is comprehensive and discerning. We conduct thorough experimental validation on two datasets of RSIs and measure network complexity by evaluating network parameters and multiadds operations. The results show that our method effectively balances computational complexity and performance. In addition, we have expanded the application of AMFFN to the field of natural image super-resolution (SR). Experimental results on five benchmark test datasets further confirm the effectiveness of our method.