公开(公告)号：US20240273682A1

公开(公告)日：2024-08-15

申请号：US18431527

申请日：2024-02-02

Applicant: NVIDIA Corporation

Inventor： Weili Nie ,  Guan-Horng Liu ,  Arash Vahdat ,  De-An Huang ,  Anima Anandkumar

IPC: G06T5/60 ,  G06T5/50

CPC classification number: G06T5/60 ,  G06T5/50

Abstract: Image restoration generally involves recovering a target clean image from a given image having noise, blurring, or other degraded features. Current image restoration solutions typically include a diffusion model that is trained for image restoration by a forward process that progressively diffuses data to noise, and then by learning in a reverse process to generate the data from the noise. However, the forward process relies on Gaussian noise to diffuse the original data, which has little or no structural information corresponding to the original data versus learning from the degraded image itself which is much more structurally informative compared to the random Gaussian noise. Similar problems also exist for other data-to-data translation tasks. The present disclosure trains a data translation conditional diffusion model from diffusion bridge(s) computed between a first version of the data and a second version of the data, which can yield a model that can provide interpretable generation, sampling efficiency, and reduced processing time.