Score: 1

Mode-Seeking for Inverse Problems with Diffusion Models

Published: December 11, 2025 | arXiv ID: 2512.10524v1

By: Sai Bharath Chandra Gutha, Ricardo Vinuesa, Hossein Azizpour

Potential Business Impact:

Fixes blurry pictures faster than before.

Business Areas:
Predictive Analytics Artificial Intelligence, Data and Analytics, Software

A pre-trained unconditional diffusion model, combined with posterior sampling or maximum a posteriori (MAP) estimation techniques, can solve arbitrary inverse problems without task-specific training or fine-tuning. However, existing posterior sampling and MAP estimation methods often rely on modeling approximations and can be computationally demanding. In this work, we propose the variational mode-seeking loss (VML), which, when minimized during each reverse diffusion step, guides the generated sample towards the MAP estimate. VML arises from a novel perspective of minimizing the Kullback-Leibler (KL) divergence between the diffusion posterior $p(\mathbf{x}_0|\mathbf{x}_t)$ and the measurement posterior $p(\mathbf{x}_0|\mathbf{y})$, where $\mathbf{y}$ denotes the measurement. Importantly, for linear inverse problems, VML can be analytically derived and need not be approximated. Based on further theoretical insights, we propose VML-MAP, an empirically effective algorithm for solving inverse problems, and validate its efficacy over existing methods in both performance and computational time, through extensive experiments on diverse image-restoration tasks across multiple datasets.

Country of Origin
πŸ‡ΊπŸ‡Έ πŸ‡ΈπŸ‡ͺ United States, Sweden

Page Count
27 pages

Category
Computer Science:
Machine Learning (CS)