Ben Poole

Google Brain

Talk Date: January 31

Talk Title: 2D Priors for 3D Generation

Abstract: Large scale datasets of images with text descriptions have enabled powerful models that represent and generate pixels. But progress in 3D generation has been slow due to the lack of 3D data and efficient architectures. In this talk, I’ll present DreamFields and DreamFusion: two approaches that enable 3D generation from 2D priors using no 3D data. By turning 2D priors into loss functions, we can optimize 3D models (NeRFs) from scratch via gradient descent. These methods enable high-quality generation of 3D objects from diverse text prompts. Finally, I’ll discuss a fundamental problem with our approach and how continued progress on pixel-space priors like Imagen Video can unlock new 3D capabilities.

Bio: Ben Poole is a research scientist at Google Brain in San Francisco working on deep generative models for images, video, and 3D. He completed his PhD at Stanford University advised by Surya Ganguli in the Neural Dynamics and Computation lab. His thesis was on computational tools to develop a better understanding of both biological and artificial neural networks. He’s worked at DeepMind, Google Research, Intel Research Pittsburgh, and the NYU Center for Neural Science.

Mark Billinghurst

Empathic Computing Laboratory and University of South Australia

Talk Date: February 21

Talk Title: Empathic Computing; New Directions for Collaborative XR

Abstract: This talk introduces Empathic Computing, a new approach for developing collaborative systems using Augmented Reality (AR) and Virtual Reality (VR). Empathic Computing combines AR, VR, and physiological sensing with machine learning to create systems that increase understanding between people. An overview of the core concepts of Empathic Computing will be given, as well as examples of current work in the field. Finally, directions for future work will be discussed in the context of the Metaverse, digital characters, AI, and other important technology trends.

Bio: Mark Billinghurst is Director of the Empathic Computing Laboratory, and Professor at the University of South Australia in Adelaide, Australia, and also at the University of Auckland in Auckland, New Zealand. He earned a PhD in 2002 from the University of Washington and conducts research on how virtual and real worlds can be merged, publishing over 700 papers on Augmented Reality, Virtual Reality, remote collaboration, Empathic Computing, and related topics. In 2013 he was elected as a Fellow of the Royal Society of New Zealand, and in 2019 was given the ISMAR Career Impact Award in recognition for lifetime contribution to AR research and commercialization. In 2022 he was inducted into the inaugural class of the IEEE VGTC VR Academy, and in 2023 elected as a Fellow of the IEEE.

Thomas Lewis

Microsoft

Talk Date: February 28

Talk Title: A Guided Tour Across the Metaverse

Abstract: The volume is increasing from news around the Metaverse as well as Mixed Reality across Virtual and Augmented Reality. It can be a bit confusing. Also, what is a Metaverse? Does the Metaverse exist today or is it a conceptual north star? Join us for a fast-paced tour of all the realities and how we can think about the Metaverse today and what it will be in the future.

Bio: Thomas Lewis is a Spatial Computing Cloud Advocate Lead in Microsoft’s Developer Relations. Thomas has worked in a variety of roles and geographies at Microsoft for over 20 years. He’s currently advocating on behalf of developers, designers, creators, and builders of Mixed Reality experiences. After putting on a Mixed Reality headset, he knew that he had experienced a taste of the future and sees the beauty, sadness, and hope that it can bring to humans.