提出新型扫描策略，提升单图像去模糊的清晰度与细节感知。
XYScanNet: A State Space Model for Single Image Deblurring
- 采用切片-扫描交替策略，更好保留像素局部依赖
- 相比同类方法，感知质量提升17%（KID指标）
- 适合追求图像真实感和细节还原的视觉恢复任务
深度状态空间模型（SSM），如近期的Mamba架构，正成为替代CNN和Transformer的有前景方案。现有基于Mamba的复原方法通过展平-扫描策略将图像块转为一维序列进行处理，但该方式忽略局部像素依赖，导致远距离像素错误相邻，降低对局部噪声的敏感性，并损害低层视觉任务中的图像锐度。为此，本文提出一种新的切片-扫描策略，交替沿片内与片间方向扫描。进一步设计用于图像去模糊的视觉状态空间模块（VSSM），并解决当前Mamba类视觉模块效率不足的问题。基于此，构建了集成轻量特征融合模块的XYScanNet架构，该模型在保持竞争性失真指标的同时，显著提升感知性能。实验表明，相较于最接近的竞争对手，其KID指标提升17%。
原文摘要 · Abstract (English)
Deep state-space models (SSMs), like recent Mamba architectures, are emerging as a promising alternative to CNN and Transformer networks. Existing Mamba-based restoration methods process visual data by leveraging a flatten-and-scan strategy that converts image patches into a 1D sequence before scanning. However, this scanning paradigm ignores local pixel dependencies and introduces spatial misalignment by positioning distant pixels incorrectly adjacent, which reduces local noise-awareness and degrades image sharpness in low-level vision tasks. To overcome these issues, we propose a novel slice-and-scan strategy that alternates scanning along intra- and inter-slices. We further design a new Vision State Space Module (VSSM) for image deblurring, and tackle the inefficiency challenges of the current Mamba-based vision module. Building upon this, we develop XYScanNet, an SSM architecture integrated with a lightweight feature fusion module for enhanced image deblurring. XYScanNet, maintains competitive distortion metrics and significantly improves perceptual performance. Experimental results show that XYScanNet enhances KID by $17\%$ compared to the nearest competitor.
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。