Inverse Problems with Diffusion Models: A MAP Estimation Perspective

TL;DR

This paper introduces a MAP estimation framework for inverse problems using diffusion models, enabling more effective image restoration by formulating the reverse process as an optimization problem with a tractable gradient.

Contribution

It presents a novel MAP-based approach to model the reverse diffusion process, allowing gradient-based optimization for inverse problems without task-specific training.

Findings

Effective algorithms for image restoration developed

Validated across multiple datasets and tasks

Framework offers new research directions for diffusion models

Abstract

Inverse problems have many applications in science and engineering. In Computer vision, several image restoration tasks such as inpainting, deblurring, and super-resolution can be formally modeled as inverse problems. Recently, methods have been developed for solving inverse problems that only leverage a pre-trained unconditional diffusion model and do not require additional task-specific training. In such methods, however, the inherent intractability of determining the conditional score function during the reverse diffusion process poses a real challenge, leaving the methods to settle with an approximation instead, which affects their performance in practice. Here, we propose a MAP estimation framework to model the reverse conditional generation process of a continuous time diffusion model as an optimization process of the underlying MAP objective, whose gradient term is tractable. In theory, the proposed framework can be applied to solve general inverse problems using gradient-based optimization methods. However, given the highly non-convex nature of the loss objective, finding a perfect gradient-based optimization algorithm can be quite challenging, nevertheless, our framework offers several potential research directions. We use our proposed formulation to develop empirically effective algorithms for image restoration. We validate our proposed algorithms with extensive experiments over multiple datasets across several restoration tasks.