Title: Mimicking of corruption in images

Abstract

Methods and systems are provided to generate an uncorrupted version of an image given an observed image that is a corrupted version of the image. In some embodiments, a corruption mimicking (“CM”) system iteratively trains a corruption mimicking network (“CMN”) to generate corrupted images given modeled images, updates latent vectors based on differences between the corrupted images and observed images, and applies a generator to the latent vectors to generate modeled images. The training, updating, and applying are performed until modeled images that are input to the CMN result in corrupted images that approximate the observed images. Because the CMN is trained to mimic the corruption of the observed images, the final modeled images represented the uncorrupted version of the observed images.

Inventors:

Anirudh, Rushil; Bremer, Peer-Timo; Jayaraman Thiagarajan, Jayaraman; Kailkhura, Bhavya

Issue Date:

2021-09-21

Research Org.:

Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Sponsoring Org.:

USDOE

OSTI Identifier:

1840475

Patent Number(s):

11126895

Application Number:

16/840,358

Assignee:

Lawrence Livermore National Security, LLC (Livermore, CA)

Patent Classifications (CPCs):

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS

Show more

G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS

G06N3/08 - Learning methods
G06N3/088 - {Non-supervised learning, e.g. competitive learning}

Show less

DOE Contract Number:  

AC52-07NA27344

Resource Type:

Patent

Resource Relation:

Patent File Date: 04/04/2020

Country of Publication:

United States

Language:

English