Patent · US Active

Diffusion-based generative modeling for synthetic data generation systems and applications

US12299962B2 · kind B2 · utility

0Cited by
2References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 4, 2022
Grant dateMay 13, 2025
Priority date
Expiry dateSep 8, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods described relate to the synthesis of content using generative models. In at least one embodiment, a score-based generative model can use a stochastic differential equation with critically-damped Langevin diffusion to learn to synthesize content. During a forward diffusion process, noise can be introduced into a set of auxiliary (e.g., “velocity”) values for an input image to learn a score function. This score function can be used with the stochastic differential equation during a reverse diffusion denoising process to remove noise from the image to generate a reconstructed version of the input image. A score matching objective for the critically-damped Langevin diffusion process can require only the conditional distribution learned from the velocity data. A stochastic differential equation based integrator can then allow for efficient sampling from these critically-damped Langevin diffusion models.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.