Linear Recurrent Unit with Semantic Modulation for Image Super-Resolution
It addresses the challenge of applying LRUs to 2D vision tasks like super-resolution, offering a more efficient and effective alternative for image restoration.
The paper proposes a linear recurrent unit (LRU) enhanced with a semantic modulating unit (SMU) for single-image super-resolution, achieving superior performance over state-of-the-art methods with comparable computational complexity.
Linear recurrent unit (LRU), designed with a principled formulation for stable linear recurrence, has demonstrated promising accuracy and robustness on long-range dependency tasks. However, its static parameterization and single-scan method limits its applicability to 2D vision tasks. In this study, we propose a LRU-based restoration network with a semantic modulating unit (SMU) to achieve a harmonious balance between performance and efficiency in single-image super-resolution. The SMU plays three key roles: LRU modulation, spatial categorization, and feature enhancement through learned prototype. Extensive experiments demonstrate that our method quantitatively and qualitatively surpasses recent state-of-the-art methods. Notably, our approach achieves superior performance with computational complexity on par with existing methods. The source code and models are available at https://github.com/MingyuChoi-run/LSM