Jonathan J Ho, 33New Brunswick, NJ

2023010, Apr 6, 2023

Oct 5, 2022

17/938139

- Mountain View CA, US
Mohammad Norouzi - Toronto, CA
William Chan - Toronto, CA
Huiwen Chang - New York NY, US
David James Fleet - Toronto, CA
Christopher Albert Lee - Manhattan NY, US
Jonathan Ho - New York NY, US
Tim Salimans - Utrecht, NL

G06N 3/08
G06V 10/80
G06V 10/82

A method includes receiving training data comprising a plurality of pairs of images. Each pair comprises a noisy image and a denoised version of the noisy image. The method also includes training a multi-task diffusion model to perform a plurality of image-to-image translation tasks, wherein the training comprises iteratively generating a forward diffusion process by predicting, at each iteration in a sequence of iterations and based on a current noisy estimate of the denoised version of the noisy image, noise data for a next noisy estimate of the denoised version of the noisy image, updating, at each iteration, the current noisy estimate to the next noisy estimate by combining the current noisy estimate with the predicted noise data, and determining a reverse diffusion process by inverting the forward diffusion process to predict the denoised version of the noisy image. The method additionally includes providing the trained diffusion model.