arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.08526eess.IVcs.CV
收藏

Blur-Attention:一种用于非均匀模糊图像恢复的提升机制

Blur-Attention: A boosting mechanism for non-uniform blurred image restoration

Beijing University of Technology(北京工业大学);Beijing Key Laboratory of Computational Intelligence and Intelligent System(计算智能与智能系统北京市重点实验室);The Hong Kong Polytechnic University(香港理工大学)

Xiaoguang Li, Feifan Yang, Kin Man Lam, Li Zhuo, Jiafeng Li

摘要:

动态场景去模糊是计算机视觉中一个具有挑战性的问题。传统方法难以准确估计空间变化的模糊核。基于数据驱动的方法通常采用无核的端到端映射方案,容易忽略核估计。为了解决这个问题,我们提出了一个模糊注意力模块动态捕捉空间变化的非均匀模糊图像的功能。该模块由一个密集块单元和一个空间注意力单元与多池特征融合,它可以有效地提取复杂的空间变化的模糊特征。我们设计了一种多级剩余连接结构,将多个模糊注意力模块连接起来,形成模糊注意力网络。通过将模糊注意力网络引入到条件生成对抗框架中,提出了一种针对单幅图像的端到端盲运动去模糊方法,即模糊注意力GAN(BAG)。该方法可以根据空间变化的模糊特征自适应地选择提取特征的权值,动态地恢复图像。实验结果表明,该方法的去模糊能力在PSNR,SSIM和主观视觉质量方面取得了优异的客观性能。此外,通过可视化的模糊注意力模块提取的特征,全面讨论其有效性。

英文摘要:

Dynamic scene deblurring is a challenging problem in computer vision. It is difficult to accurately estimate the spatially varying blur kernel by traditional methods. Data-driven-based methods usually employ kernel-free end-to-end mapping schemes, which are apt to overlook the kernel estimation. To address this issue, we propose a blur-attention module to dynamically capture the spatially varying features of non-uniform blurred images. The module consists of a DenseBlock unit and a spatial attention unit with multi-pooling feature fusion, which can effectively extract complex spatially varying blur features. We design a multi-level residual connection structure to connect multiple blur-attention modules to form a blur-attention network. By introducing the blur-attention network into a conditional generation adversarial framework, we propose an end-to-end blind motion deblurring method, namely Blur-Attention-GAN (BAG), for a single image. Our method can adaptively select the weights of the extracted features according to the spatially varying blur features, and dynamically restore the images. Experimental results show that the deblurring capability of our method achieved outstanding objective performance in terms of PSNR, SSIM, and subjective visual quality. Furthermore, by visualizing the features extracted by the blur-attention module, comprehensive discussions are provided on its effectiveness.

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。

↑