NVIDIA's Turing GPUs contain a brand new hardware accelerator for optical flow. This hardware accelerator, which is independent of CUDA cores, calculates optical flow vectors between a given frame pair at very high accuracy and high performance. This session provides a brief overview of the optical flow functionality and SDK, which was recently released by NVIDIA. We will provide a technical overview of the optical flow engine capabilities, performance and quality benchmarks and results of typical end-to-end use-cases.  Back

Pixvana's Creative Director Scott Squires & Tywen Kelly Product Manager/Evangelists will demonstrate their cloud-based GPU video processing system created for handling many large 360 videos. The talk will also showcase how VRWorks has made it possible for Pixvana to stitch multiple 8k+ videos, each from several cameras, in parallel, and how Pixvana has transformed the editing process by allowing in-headset creation of interactive experiences with branching narratives. The potential for AI and Machine Learning in VR will also be covered. 

  Back

Cory Corvus, Developer Relations Engineer at HTC Vive, will explain how Eye Tracking works with the new Vive Pro Eye and how to do Foveated Rendering with Nvidia VRS (Variable Rate Shading). Cory will review features of the Vive Pro Eye, getting started developing eye tracking, and Dynamic Foveated Rendering with NVIDIA VRS.  Back

We will present NVIDIA's solution for interactive, real-time streaming of VR content (such as games and professional applications) from the cloud to a low-powered client driving a VR/AR headset. We will outline few of the challenges, describe our  design, and share some performance and quality metrics. 

  Back

Learn how CannonDesign is using NVIDIA Holodeck to enhance its design process and break geographical boundaries through true multi-user, interactive VR sessions. We'll discuss how CannonDesign's strong collaboration with NVIDIA helped inform development of Holodeck as a tool that evolved from automotive design to architecture, engineering, and construction, and how it's changing the way designers and clients collaborate and explore spaces. We will also cover our initial challenges to adopting this technology and our current workflow, and explore internal case studies, testimonials, and production cases. This session is geared to those with basic understanding of VR workflows, as well as to experienced users who want know more about collaborative tools for VR.  Back

We'll provide an overview of new techniques developed by ZeroLight using NVIDIA's Volta and Turing GPUs to enhance real-time 3D visualization in the automotive industry for compelling retail experiences. We'll cover the challenges involved in integrating real-time ray-traced reflections at 60fps in 4k and how future developments using DXR and NVIDIA RTX will enable improvements to both graphics and performance. We'll also discuss the challenges to achieving state-of-the-art graphical quality in virtual reality. Specifically, we'll explain how the team created a compelling commercial VR encounter using StarVR One and its eye-tracking capabilities for foveated rendering.

  Back

Large AEC projects involve complex structure design and validation tools but also benefit from High-end Visualization and VR for proper scale-one immersion and volume apprehension. CADMakers has been one of the very early adopters of Dassault Systemes 3DEXPERIENCE that combines the legacy of over 20 years of CATIA CAD excellence with advanced rendering materials support and native VR immersion without the need to use other external tools. This presentation will provide an unique inside view into todays and future possibilities of decision making in building design, leveraging the power of integrated Virtual Reality and Visualization experiences that happen directly in the CAD software tools of the 3DEXPERIENCE platform. The talk will present some of the latest GPU intensive 3DEXPERIENCE platform achievements at CADMakers, including how the platform is being used for building construction simulation, visual High-End Material validation for realistic AEC design review but also actual VR usages showing the different graphics performance gains obtained with large AEC projects, as well as how VR SLI allows enabling 90FPS immersion for multi-user multi-location VR reviews. Talk will be presented with actual AEC dataset used by CADMakers for some of their buildings designed with 3DEXPERIENCE.

  Back

We'll discuss the processes and challenges of designing some of the world's most complex buildings and how adopting emerging technology can transform the design process. We'll explain how we're using NVIDIA Quaddro and RTX technologies to more efficiently manage collaboration and workflow for major international construction projects involving teams across the globe, and discuss how we're helping architects and engineers design buildings faster and more collaboratively. KPF, a leading multidisciplinary architectural practice, is pioneering a new approach to workflow that allows real-time rendering, collaborative VR and desktop virtualization.  Back

Learn how the capability of computationally lightweight augmented and mixed reality devices can be substantially enhanced using a remote rendering and streaming architecture, enabling a variety of impactful use cases of these technologies in the energy sector. NVIDIA GPUs make low-latency, collaborative streaming experiences possible on augmented and mixed reality devices through an efficient rendering and transcoding pipeline. We'll discuss technical challenges in platform development, lessons learned from adoption and utilization within Baker Hughes, a GE company, and use cases for enhanced augmented and mixed reality across the energy sector.  Back

Training a deep-learning gaze estimator requires a massive, diverse, and high-quality training set, which is challenging to produce because it requires photographing subjects and manually labeling pupil position and gaze direction accurately. We'll describe how we created anatomically informed eye and face 3D models for infrared illumination and rendering near-eye images annotated with accurate gaze labels. We use 4M synthetic eye images in combination with real-world images to train a near-eye gaze estimator for VR and AR headsets. Over a wide 40x30-degree field of view, the estimator achieves higher accuracy on real subjects than previous methods. The estimator uses an optimized network architecture that requires fewer convolutional layers than previous deep learning-based gaze trackers, achieving low latency on desktop and mobile hardware. In addition to gaze estimation, we'll show how to use the network for robust pupil estimation and accurate remote-gaze estimation.  Back

We'll discuss our team's work to determine how GPU virtualization, 5G, and edge computing, together with cutting-edge hardware and software solutions, can make cloud AR/VR a reality. Our talk will cover how 5G will shift computing and data storage to the cloud and enable new business models and commercial opportunities. We'll also talk about how 5G will enable high-resolution (4K or 8K) AR and VR, how these can revolutionize content consumption, and our role in making this possible.  Back

We'll explain how virtual reality and deep learning allowed us to radically simplify and dramatically accelerate 3D asset creation for entertainment, education, and manufacturing. With MasterpieceVR software, one of the world's first for collaborative 3D modeling, users can create 3D models without prior training, professionals can prototype 3D digital assets several times faster than traditional methods, and teams can co-create in real time. We'll explain how advances in deep learning with NVIDIA GPUs can make this process even simpler. In the coming years, users will be able to easily transform their visual ideas directly into 3D objects.  Back

We'll discuss the process of building a portable, cinematic-grade volumetric camera system powered by machine learning and describe a suite of scalable cloud processing tools using NVIDIA GPUs. We'll explain how a customized build of Unreal Engine makes it possible to play volumetric videos in VR in real time. We will also outline how volumetric videos can be streamed online through Sketchfab OSGB and Facebook GLTF format, established platforms with millions of users. In addition, we'll cover how we minimized the number of cameras needed for texturing by up-rezing our source videos from 4k to 8k using a GAN pre-trained neural network. This let us deliver cinematic-quality volumetric videos without long processing times or huge data requirements.  Back

We'll discuss recently available GPU hardware support for ray tracing, and examine how this makes it possible to fully ray-trace scenes in real time, even on high-end head-mounted displays (HMDs). Real-time ray tracing has been considered the Holy Grail of rendering, but existing solutions like NVIDIA OptiX were limited to moderate display resolutions and frame rates. As a result, they weren't feasible for ray tracing on head-mounted displays (HMDs), which typically feature a wide field of view and require constant high frame rates to avoid motion sickness. We'll examine how GPU hardware support from technologies like NVIDIA's Turing and RTX allows users to fully ray trace scenes on HMDs.  Back

Learn how to build professional VR applications with novel hardware and software features provided by NVIDIA. We will cover the latest version of OpenGL multicast (aka VR SLI) as well as Turings new hardware features Multi View Rendering as well as Variable Rate Shading. This talk is intended for software developers, while some concepts are API independent, others focus on OpenGL and/or Vulkan.  Back

We'll discuss how virtual reality and machine learning tools can help extract insights from large, complex datasets and help build effective storytelling. We'll explain why standard data analytics tools and techniques are no longer sufficient, and discuss how AI-powered visual analytics with immersive environments provide a novel and robust framework for collaborative data exploration and understanding.  Back

The trillion-dollar global construction industry suffers from chronic excess waste and critical labor shortages across the trades. VR platforms like NVIDIA's Holodeck can help solve these and other industry problems. Learn how Autodesk is partnering with NVIDIA to rethink immersive technology's role in the construction industry. We'll examine two powerful workflow strategies built to help construction teams make measurably better and faster decisions. Learn what's possible when you combine the flexibility of NVIDIA's Holodeck with a powerful data platform like Autodesk's Forge and BIM 360.  Back

Learn about the plans of market leaders in streaming VR and AR content from the cloud in this panel discussion. From enterprise use cases to streaming VR to the 5G edge, panelists will describe the state-of-the-art and challenges to making XR truly mobile.

  Back

While XR technologies are revolutionizing design reviews and contextual access to relevant information as part of product design and development, the new frontier in XR is leveraging that same 3D information and visualizations downstream in the value chain. In this panel discussion, well examine the idea of doing work in XR. Speaking with experts offering XR systems ranging from fundamental design software to providers of XR training applications, we will explore how XR is extending beyond design review and transforming a wide variety of different parts of the enterprise and value chain.  Back

David Luebke, NVIDIAs VP of Graphics Research, will give his annual address on NVIDIAs vision for the future of virtual and augmented reality. Luebke will focus on recent and ongoing research happening within NVIDIA, ranging from foveated display, to AI-powered gaze tracking, to ultra-lightweight prescription display optics, to technologies for Cloud VR beyond streaming pixels. Luebke will conclude by showcasing NVIDIAs latest developments in synthesizing virtual humans, and discuss how such technologies might be integrated with the demanding settings of virtual and augmented  reality.  Back

VR is rapidly evolving. HMD resolution and field of view are increasing, VR content is becoming more detailed, and demand for more realistic and more immersive experiences continues to grow. As we march forward in the pursuit of ever-better VR, how will we render fast enough to drive those higher resolution displays? How will we generate realistic content for enormous virtual worlds? How will we continue to enhance the quality and depth of immersion? In this panel, we'll cover topics such as human perception and neurophysiology, adaptive rendering strategies that focus compute power where it's needed, and deep learning-based synthesis for virtual models and environment. Learn how these components are being integrated to drive the future of VR.

  Back

Truly immersive virtual reality demands a display resolution and field of view that matches the human visual system. Although VR headsets continue to improve, meeting this challenge pushes the limits of per-frame computation time, bandwidth, power, and heat. We'll discuss gaze-contingent rendering, which offers an equally immersive experience at a lower cost by taking advantage of the idiosyncrasies of human peripheral vision. The spatial resolution of human perception decreases rapidly as a function of eccentricity relative to center gaze, allowing a reduced fidelity image to be displayed in the periphery without the user noticing. We'll describe our psychophysical experiment to determine the latency requirements of such a system and discuss our findings showing that state-of-the-art rendering techniques with system latencies up to 50-70 milliseconds were undetectable at the 50 percent threshold level.  Back

Learn how Microsoft is extending WebRTC to enable real-time, interactive 3D streaming from the cloud to any low-powered remote device. The purpose is to provide an open-source toolkit to enable industries to leverage remote cloud rendering in their service and product pipelines. This is required for many industries in which the scale and complexity of 3D models, scenes, physics, and rendering is beyond the capabilities of a mobile device platform. We are extending the industry standard WebRTC framework to 3D scenarios such as mixed reality. We'll explain the work we did to realize the goal of delivering high-quality 3D applications to any client — web, mobile, desktop, and embedded. This is only possible using the NVIDIA NVENCODE pipeline for server-side rendering on the cloud.

  Back

Learn how recent achievements in machine learning, sensor fusion, and GPU computing make it possible to create a next-generation advanced driver-assistance systems experience. We'll showcase a software solution that creates real-time augmented reality for drivers while using vehicle sensors, map data, telematics, and navigation guidance with a set of advanced algorithms. Our approach augments drivers' visual reality with supplementary objects in real time, and works with output devices such as head unit displays, digital clusters, and head-up displays. We'll also examine the challenges of running advanced neural network models in real time on embedded hardware and explain solutions to overcome them.  Back

While most industries have experienced growth due to rapid adoption of digital tools, productivity in architecture and construction has dropped since 2005. The industry's toolkit is limited and disjointed, imposing a ceiling on the capabilities of even the most talented designers. The result is lost time, wasted money, and an industry-wide foreclosing of creative possibility that affects the world around us. We'll discuss suite of tools developed and deployed by our team at SHoP Architects, and describe the pioneering workflows we're using to redefine the future of architecture.

  Back

We'll discuss how advancements in GPU technology, real-time ray tracing, and virtual reality technologies furthered the building design process of a global design firm. Our talk will trace the steps we took to move beyond earlier approaches to using digital technology in building design by adopting, planning, and implementing new technologies. We'll cover our firm's infrastructure and cloud technology, and conclude with a full reveal of how we deploy and embrace advanced technologies to enhance designs, enrich internal and client communication, and ultimately deliver buildings that further improve our communities.

  Back

Learn how to distribute GPU workloads on the intelligent edge with Verizon. We'll describe how Verizon engineers developed GPU virtualization and management platforms to accelerate graphics, rendering, audio, and computer vision with edge networks. We'll share recent developments in the journey to 5G and the edge by describing cases studies and demonstrating edge-based APIs for rendering and inferencing.  Back

We'll examine the potential for spatial computing and machine learning to reintroduce people to the physical potential of their bodies by focusing on Embody, MAP Lab's 2019 Sundance premiere. Inspired by movement traditions such as aikido, yoga, and dance, Embody is a social VR experience that uses visual metaphor and encouragement from teachers and friends to bring about coordinated body movement. We'll explain how this experience, which is piloted entirely by body movement and position, reclaims the body's potential inside the digital landscape. Users prompt each other with conversation, mirroring, and environmental channeling to step together through physical sequences designed to center, balance, extend, and strengthen. We hope players who experience Embody will be reminded of their deep physical potential and remember that the body is a flexible tool and able to change (http://www.sundance.org/projects/embody).

  Back

Join a special presentation from our 2018-2019 Graduate Fellowship recipients to learn what's next from the world of research and academia. Sponsored projects involve a variety of technical challenges, including topics such as 3D scene understanding, new programming models for tensor computations, HPC physics simulations for astrophysics, deep learning algorithms for AI natural language learning, and cancer diagnosis. We believe that theses students will lead the future in our industry and we're proud to support the 2018-2019 NVIDIA Graduate Fellows. For more information on the NVIDIA Graduate Fellowship program, visit www.nvidia.com/en-us/research/graduate-fellowships.  Back

Discover how more than 140 companies work together at the Khronos Group to create open, royalty-free standards that allow developers to access the power of GPUs and accelerate demanding compute, graphics, and AR/VR applications. We'll provide the latest updates on several Khronos cross-platform standards, including OpenXR for portable AR and VR, the new-generation Vulkan GPU API, the SPIR-V standard intermediate language for parallel compute and graphics, glTF for efficient transmission of 3D assets, and OpenCL for parallel heterogeneous programming. We'll also offer insights into how these open standards are supported across NVIDIA's product families.  Back