In this work we propose a new type of efficient deep-unrolling networks for solving imaging inverse problems. Classical deep-unrolling methods require full forward operator and its adjoint across each layer, and hence can be computationally more expensive than other end-to-end methods such as FBP-ConvNet, especially in 3D image reconstruction tasks. We propose a stochastic (ordered-subsets) extension of the Learned Primal-Dual (LPD) which is a state-of-the-art unrolling network. In our unrolling network, we only use subsets of the forward and adjoint operator, to achieve computational efficiency. We provide theoretical analysis of a special case within our LSPD framework, suggesting that our LSPD network has the potential to achieve the same accuracy of full batch LPD network with only accessing the subsets of operators. Our numerical results demonstrate the effectiveness of our approach in X-ray CT imaging task, showing that our networks achieve similar reconstruction accuracies as the full-batch LPD, while requiring only a fraction of the computation.
翻译:在这项工作中,我们提出了一种新型高效的深滚网络,以解决成像反向问题。古老的深滚网络需要全前端操作员及其各层之间的连接,因此可以比FBP-ConvNet等其他端到端方法更昂贵地计算,特别是在3D图像重建任务中。我们提议了一种高效的Primal-Dual(Primal-Dual)技术(LPD)扩展(有序的子集),这是一个最先进的启动网络。在我们的非滚动网络中,我们只使用前端和联合操作员的子集来实现计算效率。我们对LSPD框架内的一个特殊案例进行理论分析,建议我们的LSPD网络有可能达到完全的LPD网络的精度,只访问操作员的子集。我们的数字结果显示了我们在X射线CT成像任务中的方法的有效性,表明我们的网络实现了与全端LPD相似的重建精度,同时只需要部分计算。