Although deep neural network methods achieved much success in compressed sensing image reconstruction in recent years, they still have some issues, especially in preserving texture details. In this article, we propose a new dual-path attention network for compressed sensing image reconstruction, which is composed of a structure path, a texture path and a texture attention module. Motivated by the classical paradigm of image structure-texture decomposition, the structure path aims to reconstruct the dominant structure component of the original image, and the texture path targets at recovering the remaining texture details. To better bridge the information between two paths, the texture attention module is designed to deliver the useful structure information to the texture path and predict the texture region, thereby facilitating the recovery of texture details. Two paths are optimized with a unified loss function. In the testing phase, given the measurement vector of a new image, it can be well reconstructed by carrying out the well trained dual-path attention network and integrating the outputs of the structure path and the texture path. Experimental results on the SET5, SET11 and BSD68 testing datasets demonstrate that the proposed method achieves comparable or better results compared with some state-of-the-art deep learning based methods and conventional iterative optimization based methods in terms of reconstruction quality and robustness to noise.

中文翻译：

---

压缩感知图像重建的双路径注意力网络。

尽管近年来深度神经网络方法在压缩感测图像重建中取得了很大的成功，但它们仍然存在一些问题，尤其是在保留纹理细节方面。在本文中，我们提出了一种用于压缩感知图像重建的新型双路径注意网络，该网络由结构路径，纹理路径和纹理注意模块组成。在经典的图像结构-纹理分解范式的推动下，结构路径旨在重建原始图像的主要结构成分，而纹理路径的目标是恢复剩余的纹理细节。为了更好地在两条路径之间桥接信息，纹理注意模块设计为将有用的结构信息传递到纹理路径并预测纹理区域，从而有利于纹理细节的恢复。使用统一的损耗函数优化了两条路径。在测试阶段，给定新图像的测量向量，可以通过执行训练有素的双路径注意网络并整合结构路径和纹理路径的输出来很好地重构它。在SET5，SET11和BSD68测试数据集上的实验结果表明，与一些最新的基于深度学习的方法和基于传统迭代优化的方法相比，该方法在重建质量和抗噪性方面达到了可比或更好的结果。 。通过执行训练有素的双路径注意网络并整合结构路径和纹理路径的输出，可以很好地重构它。在SET5，SET11和BSD68测试数据集上的实验结果表明，与一些最新的基于深度学习的方法和基于传统迭代优化的方法相比，该方法在重建质量和抗噪性方面达到了可比或更好的结果。 。通过执行训练有素的双路径注意网络并整合结构路径和纹理路径的输出，可以很好地重构它。在SET5，SET11和BSD68测试数据集上的实验结果表明，与一些最新的基于深度学习的方法和基于传统迭代优化的方法相比，该方法在重建质量和抗噪性方面达到了可比或更好的结果。 。