Her co-authors were fellow researchers Yiyi Liao and Michael Niemeyer, as well as Andreas Geiger, who is group leader. Schwarz is currently a PhD student in the Autonomous Vision Group, which is split between the University of Tübingen and the MPI-IS. With GRAF, we offer an approach that vastly improves 3D-aware image synthesis for single objects and takes an important step in this direction.” Machines can already generate new 2D images really well, but science is still working on enabling them to reason better in 3D and learn abstract three-dimensional concepts. This calls for a sophisticated ability to reason in 3D that machines simply don’t have yet. “But they can do even more: they can also imagine completely new scenes because they understand the underlying concepts required to create them. “Human beings are capable of looking at a 2D image and imagining exactly what it looks like from different angles and viewpoints in 3D,” said Katja Schwarz, the paper’s lead author. One of the world’s leading machine learning conferences, NeurIPS 2020 is being held virtually until December 12. They present their work this week at the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020).
![cyber science 3d turning on 3d cyber science 3d turning on 3d](https://i.ytimg.com/vi/I7TK9F-KNPQ/hqdefault.jpg)
While science is still a long way from achieving this, researchers at the University of Tübingen and the Max Planck Institute for Intelligent Systems (MPI-IS) have taken the field one step further with GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis. The ultimate aim is enabling technologies in realms such as autonomous driving and virtual reality to operate safely and reliably.
![cyber science 3d turning on 3d cyber science 3d turning on 3d](https://thumbs.dreamstime.com/z/d-brain-concept-design-digital-graphic-abstract-geometric-background-science-network-cyber-technology-186023551.jpg)
In the field of computer vision, a key challenge lies in teaching machines to “see” and draw conclusions about complex 3D scenes, just as human beings do.