用语义调制的线性循环单元提升图像超分辨率效率与质量
Linear Recurrent Unit with Semantic Modulation for Image Super-Resolution
- 引入语义调制单元动态调节线性循环结构，增强特征表达
- 在PSNR和SSIM上超越最新方法，计算量与现有模型相当
- 适合追求高效高质图像重建的研究者与工程师
线性循环单元（LRU）因其稳定的线性递归设计，在长程依赖任务中表现出色。然而其静态参数化与单次扫描机制限制了在二维视觉任务中的应用。本文提出一种基于LRU的复原网络，融合语义调制单元（SMU），在单图像超分辨率中实现性能与效率的平衡。SMU实现三重功能：对LRU进行动态调制、实现空间类别划分、通过学习原型增强特征。大量实验表明，该方法在定量与定性指标上均优于当前最先进方法，且计算复杂度与现有方法相当。代码与模型已开源。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。