SOURCE-LINKED INTELLIGENCE

Backward SDEs-based Diffusion for Physics-Constrained Generation

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Pretrained score-based diffusion models provide strong unconditional priors, yet enforcing measurement or physics consistency in inverse problems is often handled by heuristic guidance, intermittent projections, or task-specific conditional training, with limited guarantees of feasibility at the end of inference. We propose terminal-conditioned inversion for score-based SDE priors. Given a frozen Score-SDE prior and a task-defined terminal feasibility specification, we construct an associated backward stochastic differential equation whose adapted solution defines a principled inverse map from

Read original source ↗ Open in workspace

recordType

paper

region

Global