arXiv 2511.032322026-08-04cs.CV

基于Transformer-渐进Mamba网络的轻量图像超分辨率方法

Transformer-Progressive Mamba Network for Lightweight Image Super-Resolution

Bell Honors School, Nanjing University of Posts and Telecommunications（南京邮电大学贝尔荣誉学院）；State Key Laboratory of Integrated Services Networks, Xidian University（西安电子科技大学集成服务网络国家重点实验室）；Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院模式识别与智能系统实验室）；Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院智能感知与高维信息系统教育部重点实验室）；Department of Electrical Engineering and the Institute of Communications Engineering, National Tsing Hua University（国立交通大学电子工程系与通信工程研究所）

Sichen Guo, Wenjie Li, Yuanyang Liu, Guangwei Gao, Jian Yang, Chia-Wen Lin

备注：: Accepted by TIP

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出T-PMambaSR框架，结合窗口自注意力与渐进Mamba，通过多尺度交互提升特征表示效率，引入自适应高频细化模块恢复细节，实现更高效且低计算成本的超分辨率。

摘要：

最近，基于Mamba的超分辨率方法展示了以线性复杂度捕捉全局感受野的能力，解决了Transformer方法的二次计算成本问题。然而，现有Mamba方法缺乏不同建模尺度间的精细过渡，限制了特征表示的效率。本文提出T-PMambaSR，一种轻量级超分辨率框架，整合窗口自注意力与渐进Mamba。通过在不同尺度感受野间建立交互，我们的方法建立了一种精细建模范式，逐步增强特征表示而不引入额外计算成本。此外，我们引入自适应高频细化模块（AHFRM）以恢复Transformer和Mamba处理过程中丢失的高频细节。大量实验表明，T-PMambaSR逐步增强模型的感受野和表达能力，比最近的Transformer或Mamba方法在性能上更优，同时计算成本更低。

英文摘要：

Recently, Mamba-based super-resolution (SR) methods have demonstrated the ability to capture global receptive fields with linear complexity, addressing the quadratic computational cost of Transformer-based SR approaches. However, existing Mamba-based methods lack fine-grained transitions across different modeling scales, which limits the efficiency of feature representation. In this paper, we propose T-PMambaSR, a lightweight SR framework that integrates window-based self-attention with Progressive Mamba. By enabling interactions among receptive fields of different scales, our method establishes a fine-grained modeling paradigm that progressively enhances feature representation without introducing additional computational cost. Furthermore, we introduce an Adaptive High-Frequency Refinement Module (AHFRM) to recover high-frequency details lost during Transformer and Mamba processing. Extensive experiments demonstrate that T-PMambaSR progressively enhances the model's receptive field and expressiveness, achieving competitive performance with recent Transformer- or Mamba-based methods while incurring lower computational cost. Codes will be available at https://github.com/IVIPLab/T-PMambaSR.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。