Solving Inverse Problems with a Flow-based Noise Model

2020/03/18 by Jay Whang, Qi Lei, Whang, Jay +3 · 4 citations
Computer Science · Mathematics · #FOS: Computer and information sciences #Information Theory (cs.IT) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.IT #cs.LG #math.IT #stat.ML

paper · pdf · doi:10.48550/arxiv.2003.08089

arxiv created 2021/07/01 · arxiv updated 2021/07/02

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.

Cited by

• A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors
• Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach
• Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection
• ICDM: Interference Cancellation Diffusion Models for Wireless Semantic Communications

Related

• Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching
• Composing Normalizing Flows for Inverse Problems
• Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Models
• Efficient Diffusion Posterior Sampling for Noisy Inverse Problems
• DAWN-FM: Data-Aware and Noise-Informed Flow Matching for Solving Inverse Problems