Skip to yearly menu bar Skip to main content


Poster

Solving Inverse Problems with a Flow-based Noise Model

Jay Whang · Qi Lei · Alexandros Dimakis

Keywords: [ Sparsity and Compressed Sensing ] [ Algorithms ]


Abstract:

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.

Chat is not available.