Solving Inverse Problems with a Flow-based Noise Model
Solving Inverse Problems with a Flow-based Noise Model
复制标题
DOI：
--
复制
发表时间：
2020-03
期刊：
影响因子：
--
通讯作者：
Jay Whang;Qi Lei;A. Dimakis
中科院分区：
文献类型：
--
作者：
Jay Whang;Qi Lei;A. Dimakis
我们研究了图像逆问题的归一化流先验。我们的配方认为解决方案的最大后验估计的图像条件的测量。这个公式允许我们使用具有任意依赖关系的噪声模型以及非线性前向算子。我们根据经验验证了我们的方法在各种逆问题上的有效性，包括量化测量的压缩感知和高度结构化噪声模式的去噪。我们还提出了初始的理论恢复保证解决反问题的流量之前。
We study image inverse problems with a normalizing flow prior. Our formulation views the solution as the maximum a posteriori estimate of the image conditioned on the measurements. This formulation allows us to use noise models with arbitrary dependencies as well as non-linear forward operators. We empirically validate the efficacy of our method on various inverse problems, including compressed sensing with quantized measurements and denoising with highly structured noise patterns. We also present initial theoretical recovery guarantees for solving inverse problems with a flow prior.