Artificial Intelligence unlocks Perceptual Realism in Holographic 3D Displays

Kaan Aksit, Associate Professor of Computational Light at the University College London

Presented in-person in Goergen 101 and on Zoom

Zoom Information

Zoom:https://rochester.zoom.us/j/93581409273
Meeting ID: 935 8140 9273

Abstract

Recent advances in holographic displays have opened up exciting possibilities for high-quality 3D images at interactive rates and slim eyeglasses-like form factors, ideal for Augmented Reality (AR) glasses and Virtual Reality (VR) headsets. Despite these promising developments, they often come with trade-offs such as degraded resolutions or high computational demands in exchange for small form factors or realistic 3D images. As a result, current holographic display technologies have yet to provide both realistic 3D visuals and compact hardware that could revolutionize various industries including entertainment, healthcare, communication, and work.

In this talk, I will present our novel algorithmic solutions aimed at maximizing the potential of existing holographic display hardware by addressing limitations related to computation, power, bandwidth, and brightness requirements. Throughout my presentation, I will demonstrate how these artificial intelligence fueled algorithms can be used to create new display designs with minimal hardware requirements while still delivering perceptually realistic visuals that meet human visual system's capabilities. By the end of this talk, attendees will gain insights into the research challenges in display domain, the future of holographic 3D displays and their potential impact on various industries.

Biography

Kaan Akşit is an Associate Professor of Computational Light in the Computer Science department at University College London in the United Kingdom, where Kaan also leads the Computational Light Laboratory. Kaan received his Ph.D. in electrical engineering at Koç University, Türkiye, in 2014. His M.Sc. degree is in electrical power engineering from RWTH Aachen University, Germany, in 2010. Kaan obtained his B.S. in electrical engineering from Istanbul Technical University, Türkiye, in 2007. Kaan researches the intersection of light and computation, including computational approaches in imaging, graphics, fabrication, and displays. Kaan’s research works are widely known among the optics and graphics community for his contributions to display technologies dedicated to 3D, virtual reality, and augmented reality. He worked as a research intern in Philips Research, the Netherlands, and Disney Research, Switzerland, in 2009 and 2013, respectively. In addition, he was a Senior Research Scientist at NVIDIA, in the USA, between 2014 and 2020. Over the years, Kaan’s research works has been recognized with numerous awards from various highly respected venues and institutions including ACM SIGGRAPH, IEEE VR, ISMAR and Optica.