Diffusion-based generative modeling for synthetic data generation systems and applications
US12299962B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 4, 2022 |
| Grant date | May 13, 2025 |
| Priority date | — |
| Expiry date | Sep 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.