In this paper we investigate a variety of deep learning strategies for solving inverse problems. We classify existing deep learning solutions for inverse problems into three categories of Direct Mapping, Data Consistency Optimizer, and Deep Regularizer. We choose a sample of each inverse problem type, so as to compare the robustness of the three categories, and report a statistical analysis of their differences. We perform extensive experiments on the classic problem of linear regression and three well-known inverse problems in computer vision, namely image denoising, 3D human face inverse rendering, and object tracking, selected as representative prototypes for each class of inverse problems. The overall results and the statistical analyses show that the solution categories have a robustness behaviour dependent on the type of inverse problem domain, and specifically dependent on whether or not the problem includes measurement outliers. Based on our experimental results, we conclude by proposing the most robust solution category for each inverse problem class.

翻译：在本文中,我们调查了解决反向问题的各种深层次学习策略。我们将反向问题的现有深层次学习解决方案分为三种类型:直接绘图、数据一致性优化器和深层调节器。我们选择了每种反向问题类型的样本,以比较这三类问题的稳健性,并报告对其差异的统计分析。我们对典型的线性回归问题进行了广泛的实验,对计算机视觉中的三个众所周知的反向问题进行了广泛的实验,即图像脱色、3D人面反向转换和对象跟踪,被选为每一类反向问题的代表性原型。总体结果和统计分析表明,这些解决方案类别具有依赖反向问题域类型的稳健行为,具体取决于问题是否包括计量外端。我们根据实验结果,最后为每个反向问题类别提出了最有力的解决方案类别。