Most modern imaging systems incorporate a computational pipeline to infer the image of interest from acquired measurements. The Bayesian approach for solving such ill-posed inverse problems involves the characterization of the posterior distribution of the image. This depends on the model of the imaging system and prior knowledge on the image of interest. In this work, we present a Bayesian reconstruction framework for nonlinear imaging models, where the prior knowledge on the image is specified by a deep generative model. We develop a tractable posterior sampling scheme based on the Metropolis-adjusted Langevin algorithm (MALA) for the class of nonlinear inverse problems where the forward model has a neural-network-like structure. This class includes most practical imaging modalities. We introduce the notion of augmented deep generative priors in order to suitably handle quantitative image recovery. We illustrate the advantages of our framework by applying it to two nonlinear imaging modalities-phase retrieval and optical diffraction tomography.
翻译:多数现代成像系统都包含一个计算管道,从已获得的测量结果中推断出有兴趣的图像。解决这种不正确反向问题的巴耶斯方法涉及图像后部分布特征的定性,这取决于成像系统模型和先前对感兴趣图像的了解。在这项工作中,我们为非线性成像模型提出了一个巴耶斯重建框架,先前对该图像的了解由一个深层的基因化模型具体确定。我们根据大都会调整的朗埃文算法(MALA),为前方模型具有类似神经网络结构的非线性反向问题类别开发了一个可移植的后部取样方案。这一类包括最实用的成像模式。我们引入了增强深层基因化前部的概念,以便适当处理定量成像恢复。我们通过将这一框架应用于两个非线性成像方法-级检索和光学分解图象学来说明我们的框架的优点。