PeopleofSuperintelligence

Researcher

Tianye Li

Tianye Li is a computer vision and graphics researcher whose work uses AI to reconstruct and generate digital humans and dynamic scenes. He holds a Ph.D. in computer science from USC and coauthored research on sparse-view capture, differentiable rendering, face reconstruction, and neural 3D video. After a research scientist role at Epic Games, he joined NVIDIA Research in 2023 and coauthored systems for free-viewpoint video and interactive 3D scenes. He is a Research Scientist in NVIDIA's AI-Mediated Reality and Interaction group, where his work includes generative models and dynamic reconstruction.

Now at
NVIDIA

Timeline

  1. 2016–2017

    Visiting Max Planck

    From fall 2016 to spring 2017, Li visits the Max Planck Institute for Intelligent Systems in Tübingen, working with Timo Bolkart, Javier Romero, and Michael J. Black.

  2. 2018

    Snap internship and volumetric capture

    In summer 2018, Li interns at Snap Inc. At the USC Institute for Creative Technologies, he coauthors Deep Volumetric Video From Very Sparse Multi-View Performance Capture. The method uses deep learning to reconstruct clothed human bodies from as few as three RGB sensors.

  3. 2019

    A differentiable rasterizer

    With Shichen Liu, Weikai Chen, and Hao Li, he coauthors Soft Rasterizer in 2019. The method turns mesh rendering into a differentiable process that supports 3D reconstruction from a single RGB image.

  4. 2020

    Facebook Reality Labs internship

    Li interns at Facebook Reality Labs in summer and fall 2020, hosted by Zhaoyang Lv.

  5. 2021–2022

    ToFu and neural 3D video

    In 2021, Li coauthors ToFu, a volumetric face-inference method that produces consistent meshes across identities and expressions. His 2021 arXiv paper Neural 3D Video Synthesis from Multi-view Video models dynamic scenes with a time-conditioned neural radiance field and appears at CVPR 2022.

  6. 2023

    Joining NVIDIA Research

    Li joins NVIDIA Research as a Research Scientist in 2023 after his Research Scientist role at Epic Games. He holds a computer-science Ph.D. from USC, advised by Hao Li and Randall Hill, Jr., and electrical-engineering degrees from USC and Xidian University.

  7. 2024–2025

    Free-viewpoint video systems

    At NeurIPS 2024, he coauthors QUEEN, a framework for streaming free-viewpoint video with 3D Gaussian Splatting; its quantization and sparsity design reduces several highly dynamic scenes to 0.7 MB per frame. In 2025, he coauthors Play4D, an interactive free-viewpoint video streaming pipeline for virtual-reality and light-field displays, with dynamic 4D Gaussian reconstruction for Physical AI testing in Isaac Sim.

  8. Since 2023

    NVIDIA Research Scientist

    At NVIDIA Research, Li is a Research Scientist and a member of the AI-Mediated Reality and Interaction group, where he works on digital humans, generative models, and dynamic reconstruction. In 2026, he coauthors Grounded-Exo2Ego, a dual-branch video diffusion model that couples 3D reconstruction with object-level semantic grounding to generate egocentric video from an exocentric video. The project introduces camera re-localization and synthetic training data.

Career

  1. Since 2023NVIDIAResearch Scientist
  2. Until 2023Epic GamesResearch Scientist
  3. 2020MetaResearch Intern
  4. 2018SnapResearch Intern
  5. 2016–2017Max Planck Institute for Intelligent Systems

Education

  1. University of Southern CaliforniaPhD
  2. Xidian UniversityElectrical-engineering degree

From the biography.

  1. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Tianye Li. 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.
  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. 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 named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

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

  1. Tianye Li tianyeli.github.io. Checked 20 October 2026.
  2. Deep Volumetric Video From Very Sparse Multi-View Performance Capture vgl.ict.usc.edu. Checked 20 October 2026.
  3. SoftRas vgl.ict.usc.edu. Checked 20 October 2026.
  4. Topologically Consistent Multi-View Face Inference Using Volumetric Sampling vgl.ict.usc.edu. Checked 20 October 2026.
  5. Neural 3D Video Synthesis from Multi-view Video arxiv.org. Checked 20 October 2026.
  6. Tianye Li | Research research.nvidia.com. Checked 20 October 2026.
  7. QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videos proceedings.neurips.cc. Checked 20 October 2026.
  8. Play4D - SIGGRAPH Asia 2025 Emerging Technologies research.nvidia.com. Checked 20 October 2026.
  9. Grounded-Exo2Ego — NVIDIA research.nvidia.com. Checked 20 October 2026.