PeopleofSuperintelligence

Researcher

Koki Nagano

Koki Nagano is a computer graphics and AI researcher whose work connects realistic digital humans with interactive systems. He helped develop facial-detail methods and generative avatars, then coauthored neural and Gaussian models for animatable heads. His accessible human-digitization research won the Best-in-Show award at SIGGRAPH in 2021, and his 2026 work included video generation and full-duplex speech-motion interaction. He is a principal research scientist at NVIDIA, where he focuses on human-AI interaction for agentic and physical AI.

Now at
NVIDIA
Badges

Timeline

  1. 2015

    Realistic facial skin

    In 2015, he contributes to ICT Graphics Lab research that captures facial pores and wrinkles to make digital avatars more lifelike.

  2. 2017

    A USC PhD in capture

    At USC in 2017, he defends “Multi-scale Dynamic Capture for High Quality Digital Humans,” a PhD thesis on high-fidelity 3D human capture supervised by Paul Debevec. He earns a B.E. in environmental design from Tokyo Institute of Technology and works for Weta Digital and Meta Reality Labs in Pittsburgh during his PhD.

  3. 2018–2019

    Avatar systems at Pinscreen

    At Pinscreen, he coauthors paGAN in 2018, a generative avatar method for expression-controlled face imagery. In 2019, he presents personalized real-time avatars for virtual try-on at SIGGRAPH Asia.

  4. 2021

    A SIGGRAPH Best-in-Show

    His research on accessible photorealistic human digitization wins the Best-in-Show award at SIGGRAPH in 2021.

  5. 2023

    One-shot neural head avatars

    In 2023, he coauthors Generalizable One-shot Neural Head Avatar, a model that reconstructs and animates a 3D head from a single portrait image.

  6. 2024

    GAvatar from text prompts

    In 2024, he coauthors GAvatar, which uses a primitive-based 3D Gaussian representation and implicit neural fields to generate animatable avatars from text prompts. The method renders at 100 fps at 1K resolution.

  7. 2025–2026

    Avatar generation and interaction

    In 2025, he coauthors GAIA, which uses expression-conditioned Gaussians to generate animatable 3D head avatars. In June 2026, he coauthors DyaPlex, a streaming model that synchronizes speech and motion for dyadic interaction. In August 2026, he coauthors Grounded-Exo2Ego, a video diffusion model that generates egocentric video from exocentric footage with geometric anchoring and semantic grounding.

  8. As of October 2026

    Principal research scientist at NVIDIA

    His current research focuses on human-AI interaction for agentic and physical AI. He joins NVIDIA Research in 2020 after serving as a principal scientist at Pinscreen and is a principal research scientist there as of October 2026.

Career

  1. Since 2020NVIDIAPrincipal research scientist
  2. Until 2020PinscreenPrincipal scientist

Education

  1. 2017University of Southern CaliforniaPhD
  2. Institute of Science TokyoB.E. in environmental design

From the biography.

  1. 16% of AI career moves in the 2020s went from a university to a companyIncludes Koki Nagano. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  2. 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.
  3. 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.
  4. 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.

Colleagues

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

Sources and credits

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

  1. Fast Company and Gizmodo Feature Graphics Lab Innovations for Creating Realistic Skin ict.usc.edu. Checked 20 October 2026.
  2. PhD Defense- Koki Nagano viterbi.usc.edu. Checked 20 October 2026.
  3. KOKI NAGANO luminohope.org. Checked 20 October 2026.
  4. Presenter - SIGGRAPH Asia 2024 asia.siggraph.org. Checked 20 October 2026.
  5. paGAN: Real-time Avatars Using Dynamic Textures vgl.ict.usc.edu. Checked 20 October 2026.
  6. Real-Time Live: Personalized Avatars for Realtime Virtual Try-on sa2019.conference-program.com. Checked 20 October 2026.
  7. Generalizable One-shot Neural Head Avatar research.nvidia.com. Checked 20 October 2026.
  8. GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning openaccess.thecvf.com. Checked 20 October 2026.
  9. GAIA: Generative Animatable Interactive Avatars with Expression-conditioned Gaussians research.nvidia.com. Checked 20 October 2026.
  10. Koki Nagano | NVIDIA AI-Mediated Reality and Interaction Research research.nvidia.com. Checked 20 October 2026.
  11. DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction arxiv.org. Checked 20 October 2026.
  12. Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation arxiv.org. Checked 20 October 2026.
  13. Koki Nagano | Research research.nvidia.com. Checked 20 October 2026.