Dual-Path Large Kernel Learning and Its Applications in Single-Image Super-Resolution

• Published in: Sensors (Basel, Switzerland) Vol. 24; no. 19; p. 6174
• Main Authors: Su, Zhen, Sun, Mang, Jiang, He, Ma, Xiang, Zhang, Rui, Lv, Chen, Kou, Qiqi, Cheng, Deqiang
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.10.2024; MDPI
• Subjects: Algorithms; Artificial intelligence; Comparative analysis; Decomposition; dual path; Efficiency; Image processing; Image retrieval; large kernel learning; lightweight; Machine learning; Methods; Neural networks; super-resolution; China; large kernel learning; dual path; super-resolution; lightweight
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s24196174

To enhance the performance of super-resolution models, neural networks frequently employ module stacking. However, this approach inevitably results in an excessive proliferation of parameter counts and information redundancy, ultimately constraining the deployment of these models on mobile devices. To surmount this limitation, this study introduces the application of Dual-path Large Kernel Learning (DLKL) to the task of image super-resolution. Within the DLKL framework, we harness a multiscale large kernel decomposition technique to efficiently establish long-range dependencies among pixels. This network not only maintains excellent performance but also significantly mitigates the parameter burden, achieving an optimal balance between network performance and efficiency. When compared with other prevalent algorithms, DLKL exhibits remarkable proficiency in generating images with sharper textures and structures that are more akin to natural ones. It is particularly noteworthy that on the challenging texture dataset Urban100, the network proposed in this study achieved a significant improvement in Peak Signal-to-Noise Ratio (PSNR) for the ×4 upscaling task, with an increase of 0.32 dB and 0.19 dB compared with the state-of-the-art HAFRN and MICU networks, respectively. This remarkable result not only validates the effectiveness of the present model in complex image super-resolution tasks but also highlights its superior performance and unique advantages in the field.