AI Case Study

Google DeepMind plans to build complete 3D models from a few pictures using generative query network

Deepmind, a Google subsidiary, is developing a generative query network model to develop 3D models from various angles from a handful of 2D images by accurately estimating different dimensions. The model is expected to find application in robotics and military.

Industry

Technology

Internet Services Consumer

Project Overview

"After viewing something from just a few different perspectives, the Generative Query Network was able to piece together an object’s appearance, even as it would appear from angles not analyzed by the algorithm, according to research published today in Science. And it did so without any human supervision or training. That could save a lot of time as engineers prepare increasingly advanced algorithms for technology, but it could also extend the abilities of machine learning to give robots (military or otherwise) greater awareness of their surroundings.

The GQN or Generative Query Network can render an object or scene from any angle even if it's only fed with handful of 2D images. The algorithm is capable of 'imagining' how the scene might look like from relatively low input of data and can render unseen sides of the object and generate a 3D view from multiple angles without leveraging large datasets for supervision or training. "

Reported Results

Research; results not yet available. However several applications in Robotics, Military etc

Technology

Generative Query Network

Function

R And D

Core Research And Development

Background

Deepmind, a Google subsidiary, is developing a generative query network model to develop 3D models from a few pictures

Benefits

Data