PeopleofSuperintelligence

Researcher

Michael Stengel

Michael Stengel is a computer graphics researcher at NVIDIA whose work brings AI into gaze estimation, 3D rendering, and video generation. He completed a PhD at TU Braunschweig in 2016 and joined NVIDIA as a research scientist in 2017. His projects include NVGaze, networked light-probe streaming, AI-mediated 3D video conferencing, Play4D, and interactive radiance-field rendering. In August 2026, he coauthored Grounded-Exo2Ego, a video diffusion system for generating egocentric views from exocentric footage, and remains a research scientist at NVIDIA.

Now at
NVIDIA
Works
34
Citations
1,140
h-index
16
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2016

    A PhD at TU Braunschweig

    In 2016, he completes a PhD at TU Braunschweig.

  2. 2017

    Joining NVIDIA Research

    He joins NVIDIA as a Research Scientist in 2017, working on augmented and virtual reality, perceptual real-time rendering, and hyperscale graphics systems.

  3. 2019

    NVGaze for near-eye gaze

    In 2019, he coauthors NVGaze, which builds synthetic and real-world near-eye datasets and trains a neural network for gaze estimation at sub-millisecond latency.

  4. 2021

    Streaming dynamic light probes

    In 2021, he coauthors a system for streaming ray-traced global illumination from a server to thin clients through a networked graphics pipeline using dynamic irradiance probes.

  5. 2023

    AI-mediated 3D video conferencing

    At SIGGRAPH 2023, he coauthors a video-conferencing system that encodes a 2D image as a triplanar neural representation and renders a life-sized talking head from new viewpoints in real time.

  6. 2025

    Play4D for dynamic scenes

    In 2025, he coauthors Play4D, a method for dynamic 4D scene reconstruction for Physical AI testing in Isaac Sim, with compressed streaming and free-viewpoint viewing on VR and light-field displays.

  7. August 2025–June 2026

    Radiance fields on light-field displays

    In August 2025, he coauthors a framework that renders radiance fields on light-field displays using shared intermediate sweeping planes. On a Looking Glass display, it reaches 200+ FPS at 512p across 45 views; the authors revise the paper in June 2026.

  8. August 2026

    Research Scientist at NVIDIA

    In August 2026, he coauthors Grounded-Exo2Ego, a dual-branch video diffusion model that uses 3D reconstruction and object-level semantic grounding to generate egocentric video from exocentric footage. He remains a Research Scientist at NVIDIA, a role he has held since 2017, with interests in augmented and virtual reality, perceptual real-time rendering, and hyperscale graphics systems.

Career

  1. Since 2017NVIDIAResearch Scientist

Education

  1. 2016Technische Universität BraunschweigPhD

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. Near‐Eye Display and Tracking Technologies for Virtual and Augmented Reality2019 · Computer Graphics Forum · 227 citations
  2. Foveated AR2019 · ACM Transactions on Graphics · 156 citationsWith David Luebke
  3. NVGaze2019 · CHI Conference on Human Factors in Computing Systems · 138 citationsWith David Luebke, Samuli Laine and Shalini De Mello
  4. Adaptive Image-Space Sampling for Gaze-Contingent Real-time Rendering2016 · Computer Graphics Forum · 88 citations
  5. Perception-driven Accelerated Rendering2017 · Computer Graphics Forum · 76 citations

From OpenAlex, as of 21 October 2026.

  1. Google has the highest combined h-index among AI organizationsIncludes NVIDIA. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  2. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes NVIDIA. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  3. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes NVIDIA. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.
  4. Universities (31%) and startups and other companies (25%) employ the largest shares of 2020–2026 entrantsIncludes NVIDIA. Among 819 people whose first recorded role started in 2020–2026 and who have a known current organization, 60% work in commercial sectors (25% at startups and other companies, 23% at frontier labs and 13% at big tech, with 9 in two), and 31% work at universities, compared with 66% for earlier entrants.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Michael Stengel yet. Send us a free-licensed photo.

  1. Michael Stengel | NVIDIA AI-Mediated Reality and Interaction Research research.nvidia.com. Checked 20 October 2026.
  2. NVGaze: An Anatomically-Informed Dataset for Low-Latency, Near-Eye Gaze Estimation | Research research.nvidia.com. Checked 20 October 2026.
  3. [2103.05875] A Distributed, Decoupled System for Losslessly Streaming Dynamic Light Probes to Thin Clients arxiv.org. Checked 20 October 2026.
  4. AI-Mediated 3D Video Conferencing | Research research.nvidia.com. Checked 20 October 2026.
  5. Tianye Li tianyeli.github.io. Checked 20 October 2026.
  6. [2508.18540] Real-time 3D Visualization of Radiance Fields on Light Field Displays arxiv.org. Checked 20 October 2026.
  7. [2608.20534] Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation arxiv.org. Checked 20 October 2026.