Score: 1

A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models

Published: September 23, 2025 | arXiv ID: 2509.19276v1

By: Tim Y. J. Wang, O. Deniz Akyildiz

Potential Business Impact:

Lets computers fix blurry pictures perfectly.

Business Areas:
Water Purification Sustainability

Solving ill-posed inverse problems requires powerful and flexible priors. We propose leveraging pretrained latent diffusion models for this task through a new training-free approach, termed Diffusion-regularized Wasserstein Gradient Flow (DWGF). Specifically, we formulate the posterior sampling problem as a regularized Wasserstein gradient flow of the Kullback-Leibler divergence in the latent space. We demonstrate the performance of our method on standard benchmarks using StableDiffusion (Rombach et al., 2022) as the prior.

Country of Origin
🇬🇧 United Kingdom

Page Count
12 pages

Category
Statistics:
Machine Learning (Stat)