MambaCSR：基于SSM的压缩图像超分辨率双交错扫描方法
MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMs
AI总结：
针对压缩图像超分辨率任务，提出基于Mamba的MambaCSR框架，通过双交错扫描范式（含分层、水平-垂直交错扫描）及位置对齐跨尺度扫描，在多基准上取得优异性能，代码即将开源。
摘要：
我们提出MambaCSR，这是一个基于Mamba的简单但有效的框架，用于具有挑战性的压缩图像超分辨率（CSR）任务。尽管Mamba依赖于所有token的选择性状态空间建模，但它的扫描策略对于恢复过程中有效的上下文知识建模至关重要。在这项工作中，我们为CSR提出了一种高效的双交错扫描范式（DIS），该范式由两种扫描策略组成：（i）分层交错扫描，通过同时利用基于局部窗口的扫描和顺序扫描方法，全面捕获和利用图像中最具潜力的上下文信息；（ii）水平到垂直交错扫描，通过消除不同方向扫描之间的冗余来降低计算成本。为了克服非均匀压缩伪影，我们还提出了位置对齐的跨尺度扫描来建模多尺度上下文信息。在多个基准上的实验结果表明，我们的MambaCSR在压缩图像超分辨率任务中表现出色。代码将很快在https://github.com/renyulin-f/MambaCSR上提供。
英文摘要：
We present MambaCSR, a simple but effective framework based on Mamba for the challenging compressed image super-resolution (CSR) task. Particularly, the scanning strategies of Mamba are crucial for effective contextual knowledge modeling in the restoration process despite it relying on selective state space modeling for all tokens. In this work, we propose an efficient dual-interleaved scanning paradigm (DIS) for CSR, which is composed of two scanning strategies: (i) hierarchical interleaved scanning is designed to comprehensively capture and utilize the most potential contextual information within an image by simultaneously taking advantage of the local window-based and sequential scanning methods; (ii) horizontal-to-vertical interleaved scanning is proposed to reduce the computational cost by leaving the redundancy between the scanning of different directions. To overcome the non-uniform compression artifacts, we also propose position-aligned cross-scale scanning to model multi-scale contextual information. Experimental results on multiple benchmarks have shown the great performance of our MambaCSR in the compressed image super-resolution task. The code will be soon available in~\textcolor{magenta}{\url{https://github.com/renyulin-f/MambaCSR}}.
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。
