Constrained Synthesis with Projected Diffusion Models

Part of Advances in Neural Information Processing Systems 37 (NeurIPS 2024) Main Conference Track

Bibtex Paper Supplemental

Authors

Jacob K Christopher, Stephen Baek, Nando Fioretto

Abstract

This paper introduces an approach to endow generative diffusion processes the ability to satisfy and certify compliance with constraints and physical principles. The proposed method recast the traditional sampling process of generative diffusion models as a constrained optimization problem, steering the generated data distribution to remain within a specified region to ensure adherence to the given constraints.These capabilities are validated on applications featuring both convex and challenging, non-convex, constraints as well as ordinary differential equations, in domains spanning from synthesizing new materials with precise morphometric properties, generating physics-informed motion, optimizing paths in planning scenarios, and human motion synthesis.