Patent · US Active

Enhanced video shot matching using generative adversarial networks

US11158090B2 · kind B2 · utility

1Cited by

3References

20Claims

0Family size

Assignee

Adobe Inc. · US

Inventors

Tharun Mohandoss · Narayanpur, IN
Pulkit Gera · Gairsain, IN
Oliver Wang · Seattle, US
Kartik Sethi · Krishna Nagar, IN
Kalyan Sunkavalli · San Jose, US
Elya Shechtman · Seattle, US
Chetan Nanda · New Delhi, IN

Key dates

Filing date	Nov 22, 2019
Grant date	Oct 26, 2021
Priority date	—
Expiry date	Jan 29, 2040

Classification

Technology area (CPC H)Electricity
CPC primaryH04N1/6086
WIPO fieldAudio-visual technology
WIPO sectorElectrical engineering

Abstract

This disclosure involves training generative adversarial networks to shot-match two unmatched images in a context-sensitive manner. For example, aspects of the present disclosure include accessing a trained generative adversarial network including a trained generator model and a trained discriminator model. A source image and a reference image may be inputted into the generator model to generate a modified source image. The modified source image and the reference image may be inputted into the discriminator model to determine a likelihood that the modified source image is color-matched with the reference image. The modified source image may be outputted as a shot-match with the reference image in response to determining, using the discriminator model, that the modified source image and the reference image are color-matched.

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