Learning Gradually Non-convex Image Priors Using Score Matching

02/21/2023
by   Erich Kobler, et al.
0

In this paper, we propose a unified framework of denoising score-based models in the context of graduated non-convex energy minimization. We show that for sufficiently large noise variance, the associated negative log density – the energy – becomes convex. Consequently, denoising score-based models essentially follow a graduated non-convexity heuristic. We apply this framework to learning generalized Fields of Experts image priors that approximate the joint density of noisy images and their associated variances. These priors can be easily incorporated into existing optimization algorithms for solving inverse problems and naturally implement a fast and robust graduated non-convexity mechanism.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset