Solving Inverse Problems with FLAIR

TL;DR

FLAIR is a novel, training-free variational framework that uses flow-based generative models as priors for inverse imaging problems, achieving superior reconstruction quality and diversity without requiring model training.

Contribution

Introduces FLAIR, a training-free variational method leveraging flow models as priors, with a flow matching objective and data consistency enforcement for inverse problems.

Findings

Outperforms existing diffusion- and flow-based methods in reconstruction quality.

Demonstrates consistent improvements across standard imaging benchmarks.

Provides a flexible, data-agnostic approach to inverse problems.

Abstract

Flow-based latent generative models such as Stable Diffusion 3 are able to generate images with remarkable quality, even enabling photorealistic text-to-image generation. Their impressive performance suggests that these models should also constitute powerful priors for inverse imaging problems, but that approach has not yet led to comparable fidelity. There are several key obstacles: (i) the data likelihood term is usually intractable; (ii) learned generative models cannot be directly conditioned on the distorted observations, leading to conflicting objectives between data likelihood and prior; and (iii) the reconstructions can deviate from the observed data. We present FLAIR, a novel, training-free variational framework that leverages flow-based generative models as prior for inverse problems. To that end, we introduce a variational objective for flow matching that is agnostic to the type of degradation, and combine it with deterministic trajectory adjustments to guide the prior towards regions which are more likely under the posterior. To enforce exact consistency with the observed data, we decouple the optimization of the data fidelity and regularization terms. Moreover, we introduce a time-dependent calibration scheme in which the strength of the regularization is modulated according to off-line accuracy estimates. Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity. Our code is available at https://inverseflair.github.io/.