FreeTransformSR：基于自由低秩可学习变换的高效轻量级图像超分辨率
FreeTransformSR: Efficient Lightweight Image Super-Resolution via Free Low-Rank Learnable Transform
浏览论文内容
中文总结 AI 辅助
提出基于自由低秩可学习变换的轻量级超分辨率网络FreeTransformSR，通过自适应特征调制与动态融合，以595K参数在多个基准上取得竞争性能。
中文摘要 AI 辅助
单图像超分辨率旨在从低分辨率输入重建高分辨率图像。本文提出FreeTransformSR，一种基于通道级自由低秩可学习变换的新型轻量级超分辨率网络。该变换以数据驱动方式学习任务自适应基函数，以极小的参数开销实现自适应特征调制。为进一步增强高频细节恢复，我们引入局部特征调制分支，通过深度卷积补充变换域处理。此外，软复杂度自适应模块通过轻量级门控网络动态融合局部卷积与窗口自注意力分支的输出，根据区域纹理特征自适应调整融合比例。还纳入自适应强度调制策略，在样本级别调整变换域响应强度，使网络能根据输入特征动态调整处理强度。在五个基准数据集上的大量实验表明，FreeTransformSR以显著更少的参数和FLOPs实现了具有竞争力的PSNR/SSIM性能。具体而言，FreeTransformSR在BSD100 x2上达到32.41 dB，在Urban100 x4上达到27.00 dB，仅需595K参数，同时推理速度优于对比方法，非常适合资源受限场景下的部署。源代码可在以下网址获取：this https URL。
英文摘要
Single image super-resolution aims to reconstruct high-resolution images from low-resolution inputs. This paper proposes FreeTransformSR, a novel lightweight super-resolution network based on a channel-wise free low-rank learnable transform. The transform learns task-adaptive basis functions in a data-driven manner, enabling adaptive feature modulation with minimal parameter overhead. To further enhance high-frequency detail recovery, we introduce a local feature modulation branch that complements transform-domain processing with depthwise convolution. In addition, a soft complexity adaptive module dynamically fuses the outputs of local convolution and window self-attention branches through a lightweight gating network, adaptively adjusting the fusion ratio based on regional texture characteristics. An adaptive intensity modulation strategy is also incorporated to adjust transform-domain response strength at the sample level, enabling the network to dynamically adjust processing intensity according to input features. Extensive experiments on five benchmark datasets demonstrate that FreeTransformSR achieves competitive PSNR/SSIM performance with significantly fewer parameters and FLOPs. Specifically, FreeTransformSR achieves 32.41 dB on BSD100 x2 and 27.00 dB on Urban100 x4 with only 595K parameters, while delivering faster inference speed than competing methods, making it well-suited for deployment in resource-constrained scenarios. Source code is available at: https://github.com/HJiLi/FreeTransformSR.
发表机构
- Chinese Academy of Sciences Changchun Institute of Optics Fine Mechanics and Physics（中国科学院长春光学精密机械与物理研究所）
- University of the Chinese Academy of Sciences（中国科学院大学）
机构由 AI 辅助整理，请以论文原文为准。
