IVCVJan 25, 2025

MAP-based Problem-Agnostic diffusion model for Inverse Problems

arXiv:2501.15128v21 citationsh-index: 1
Originality Incremental advance
AI Analysis

This work addresses inverse problems in image processing, offering a novel approach that is incremental in enhancing diffusion models for conditional generation tasks.

The paper tackles the challenge of solving inverse problems in image processing by proposing a problem-agnostic diffusion model that uses a MAP-based guided term estimation method, resulting in improved performance such as better content preservation in super-resolution and inpainting tasks compared to state-of-the-art methods.

Diffusion models have indeed shown great promise in solving inverse problems in image processing. In this paper, we propose a novel, problem-agnostic diffusion model called the maximum a posteriori (MAP)-based guided term estimation method for inverse problems. To leverage unconditionally pretrained diffusion models to address conditional generation tasks, we divide the conditional score function into two terms according to Bayes' rule: an unconditional score function (approximated by a pretrained score network) and a guided term, which is estimated using a novel MAP-based method that incorporates a Gaussian-type prior of natural images. This innovation allows us to better capture the intrinsic properties of the data, leading to improved performance. Numerical results demonstrate that our method preserves contents more effectively compared to state-of-the-art methods--for example, maintaining the structure of glasses in super-resolution tasks and producing more coherent results in the neighborhood of masked regions during inpainting.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes