论文标题
通过基于流的噪声模型解决反问题
Solving Inverse Problems with a Flow-based Noise Model
论文作者
论文摘要
我们研究图像逆问题，并以归一流的流量为准。我们的公式将解决方案视为在测量上条件的图像的最大后验估计值。该公式使我们能够使用具有任意依赖性的噪声模型以及非线性远期操作员。我们从经验上验证了我们方法对各种反问题的疗效，包括通过量化测量值进行压缩感测，并使用高度结构化的噪声模式进行降解。我们还提供了最初的理论恢复保证，以解决先验流量的反问题。
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.
