Details

Autor(en) / Beteiligte

• Eslami, S M Ali
• Jimenez Rezende, Danilo
• Besse, Frederic
• Viola, Fabio
• Morcos, Ari S
• Garnelo, Marta
• Ruderman, Avraham
• Rusu, Andrei A
• Danihelka, Ivo
• Gregor, Karol
• Reichert, David P
• Buesing, Lars
• Weber, Theophane
• Vinyals, Oriol
• Rosenbaum, Dan
• Rabinowitz, Neil
• King, Helen
• Hillier, Chloe
• Botvinick, Matt
• Wierstra, Daan
• Kavukcuoglu, Koray
• Hassabis, Demis

Titel

Neural scene representation and rendering

Ist Teil von

• Science (American Association for the Advancement of Science), 2018-06, Vol.360 (6394), p.1204-1210

Ort / Verlag

United States: The American Association for the Advancement of Science

Erscheinungsjahr

2018

Quelle

Science Online_科学在线

Beschreibungen/Notizen

• Scene representation-the process of converting visual sensory data into concise descriptions-is a requirement for intelligent behavior. Recent work has shown that neural networks excel at this task when provided with large, labeled datasets. However, removing the reliance on human labeling remains an important open problem. To this end, we introduce the Generative Query Network (GQN), a framework within which machines learn to represent scenes using only their own sensors. The GQN takes as input images of a scene taken from different viewpoints, constructs an internal representation, and uses this representation to predict the appearance of that scene from previously unobserved viewpoints. The GQN demonstrates representation learning without human labels or domain knowledge, paving the way toward machines that autonomously learn to understand the world around them.