SOURCE-LINKED INTELLIGENCE

Diffusion Based Unpaired Data Learning for Inverse Problems

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Data is important in many deep learning-based inverse problem solvers. However, obtaining sufficient paired data in many scenarios remains highly challenging, while unpaired data is cheap. To maximize data utilization, this paper proposes LUD-DIF, a diffusion-based approach for solving inverse problems with unpaired data. Starting from the evidence lower bound (ELBO) of the joint distribution, we decouple it into two independent diffusion processes under the weak-coupling assumption. The method provides theoretical support from a variational inference perspective, derives the loss function, qu

Read original source ↗ Open in workspace

recordType

paper

region

Global