用于图像去模糊的高效视觉状态空间模型
Efficient Visual State Space Model for Image Deblurring
AI总结：
针对ViT高分辨率图像去模糊计算复杂度高的问题，提出高效视觉状态空间模型EVSSM，通过几何变换扫描和判别频域前馈网络兼顾效率与性能，效果优于现有最优方法。
摘要：
卷积神经网络（CNNs）和视觉Transformer（ViTs）在图像复原任务中已取得优异性能。尽管ViTs凭借有效捕捉长距离依赖和输入特定特征的能力，整体表现优于CNNs，但其计算复杂度随图像分辨率呈二次增长，这一局限阻碍了其在高分辨率图像复原中的实际应用。\n本文提出一种简洁高效的视觉状态空间模型EVSSM用于图像去模糊，充分发挥状态空间模型（SSMs）在视觉数据处理上的优势。现有方法采用多种固定方向扫描进行特征提取，会显著增加计算成本；与之不同，我们设计了高效视觉扫描模块，在每个基于SSM的模块前施加多种几何变换，既能捕捉有用的非局部信息，又能保持高效率。此外，为更有效地捕捉和表征局部信息，我们提出了基于高效判别频域的前馈网络EDFFN，可有效估计潜在清晰图像复原所需的有用频率信息。\n大量实验结果表明，所提出的EVSSM在基准数据集和真实世界图像上的表现均优于当前最优方法。代码已开源至https://github.com/kkkls/EVSSM。
英文摘要：
Convolutional neural networks (CNNs) and Vision Transformers (ViTs) have achieved excellent performance in image restoration. While ViTs generally outperform CNNs by effectively capturing long-range dependencies and input-specific characteristics, their computational complexity increases quadratically with image resolution. This limitation hampers their practical application in high-resolution image restoration. In this paper, we propose a simple yet effective visual state space model (EVSSM) for image deblurring, leveraging the benefits of state space models (SSMs) for visual data. In contrast to existing methods that employ several fixed-direction scanning for feature extraction, which significantly increases the computational cost, we develop an efficient visual scan block that applies various geometric transformations before each SSM-based module, capturing useful non-local information and maintaining high efficiency. In addition, to more effectively capture and represent local information, we propose an efficient discriminative frequency domain-based feedforward network (EDFFN), which can effectively estimate useful frequency information for latent clear image restoration. Extensive experimental results show that the proposed EVSSM performs favorably against state-of-the-art methods on benchmark datasets and real-world images. The code is available at https://github.com/kkkls/EVSSM.
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。
