Title:
Deep Learning and Computer Graphics

Abstract:
David Luebke, NVIDIA’s VP of Graphics Research, will describe NVIDIA’s vision for the intersection of machine learning and computer graphics. Luebke will describe recent research results using deep neural networks for a variety of graphics problems, ranging from material capture, to facial and character animation, to image denoising and super-resolution, to generating realistic images of human faces with no 3D models at all. He will conclude with some thoughts about future directions for graphics and graphics hardware given developments in deep learning and real-time ray tracing.

Bio:
Dr. David Luebke helped found NVIDIA Research in 2006 after eight years on the Computer Science faculty of the University of Virginia. Before that he received his Ph.D. under Frederick P. Brooks at the University of North Carolina. Today he run NVIDIA's research efforts at the intersection of computer graphics, machine learning, and virtual & augmented reality. Together with his colleagues David has written a book, created a major VR museum exhibit visited by over 110,000 people, taught an online course on parallel computing that has reached over 100,000 students, and authored