Google Inc.

Wenchao Tong

Ce Liu

Dilip Krishnan

Jingbin Wang

Mikael Bonnevie

Michael Krainin

Aaron Joseph Maschinot

Hossein Talebi

Piotr Teterwak

Aaron Yehuda Sarna

Shuchao Bi

Haifeng Gong

Raanan Sayag

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating realistic extensions of images. In one aspect, a method comprises providing an input that comprises a provided image to a generative neural network having a plurality of generative neural network parameters. The generative neural network processes the input in accordance with trained values of the plurality of generative neural network parameters to generate an extended image. The extended image has (i) more rows, more columns, or both than the provided image, and (ii) is predicted to be a realistic extension of the provided image. The generative neural network is trained using an adversarial loss objective function.

Image extension neural networks

Growing community of inventors

San Jose, CA, United States of America

Wenchao Tong