PeopleofSuperintelligence

Researcher

Matthew Chan

Also known as Matthew Aaron Chan

Matthew Chan is an NVIDIA researcher working where computer graphics meets generative AI, on models that learn 3D faces, heads and scenes from 2D images. After earning a bachelor's degree in mathematics and computer science from the University of Maryland, College Park, in 2021, they were one of four equal-contribution authors of EG3D, a 3D generative adversarial network by Stanford and NVIDIA researchers that became a CVPR oral paper in 2022. They joined NVIDIA as a research engineer in 2022, and in 2023 coauthored Live 3D Portrait, an AI-mediated 3D video conferencing system shown at SIGGRAPH, and the GeNVS diffusion model. Their recent papers include What You See Is What You GAN in 2024, the animatable Gaussian head avatars of GAIA at SIGGRAPH 2025, and real-time radiance field rendering for light field displays, presented at High-Performance Graphics in July 2026.

Now at
NVIDIA
Works
12
Citations
1,289
h-index
3
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2021

    Mathematics and computer science at Maryland

    They graduate from the University of Maryland, College Park, in 2021 with a bachelor's degree in mathematics and computer science.

  2. 2021–2022

    EG3D with Stanford and NVIDIA

    In 2021, Chan coauthors EG3D with Eric R. Chan, Koki Nagano, Gordon Wetzstein and others, as one of four equal-contribution authors and with a Stanford University affiliation. Its hybrid explicit-implicit architecture builds on StyleGAN2 to synthesize high-resolution, multi-view-consistent images in real time along with high-quality 3D geometry. The paper is an oral presentation at CVPR in June 2022.

  3. 2022

    Research engineer at NVIDIA

    They join NVIDIA as a research engineer in 2022. Their work sits between graphics and generative models, with a special interest in generative 3D representations and in 3D scene synthesis, reconstruction and understanding.

  4. 2023

    Live 3D Portrait and video calls

    Live 3D Portrait, published at SIGGRAPH 2023, turns a single unposed portrait photo into a triplane neural radiance field that renders at 24 fps on consumer hardware. At SIGGRAPH Emerging Technologies 2023, Chan and NVIDIA colleagues show an AI-mediated 3D video conferencing system that streams a life-sized talking head from a single webcam to a Looking Glass light field display.

  5. October 2023

    GeNVS at ICCV

    In October 2023, they and their coauthors present GeNVS as an oral paper at ICCV 2023. The diffusion model generates 3D-aware novel views from as few as a single input image by adding a 3D feature volume to existing 2D diffusion backbones.

  6. 2024

    High-fidelity geometry in 3D GANs

    In January 2024, they post What You See Is What You GAN, whose learned samplers use up to 5 times fewer depth samples so a 3D GAN can render every pixel at full resolution. In April 2024, they speak on learning photorealistic 3D digital humans from in-the-wild photos at a joint event of the Silicon Valley ACM SIGGRAPH, San Francisco Bay Area ACM and Los Angeles ACM SIGGRAPH chapters.

  7. 2025

    Portrait videos and GAIA avatars

    At CVPR 2025, Chan coauthors a triplane fusion method that reconstructs coherent 3D portrait videos from a single camera for telepresence. GAIA, presented at SIGGRAPH 2025 in Vancouver in August 2025, generates animation-ready 3D Gaussian head avatars learned only from in-the-wild image datasets.

  8. July 2026

    Radiance fields on light field displays

    In July 2026, they and eight NVIDIA colleagues present a framework for real-time radiance field rendering on light field displays at High-Performance Graphics 2026 in Los Angeles. The method reaches more than 200 frames per second for 45 views at 512p on an RTX 5090.

Career

  1. Since 2022NVIDIAResearch Engineer
  2. 2024–2026University of Maryland

Education

  1. 2021University of MarylandBachelor's degree in mathematics and computer science

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

Most-cited works

  1. Efficient Geometry-aware 3D Generative Adversarial Networks2022 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 1,116 citationsWith Gordon Wetzstein, Shalini De Mello and Tero Karras
  2. Generative Novel View Synthesis with 3D-Aware Diffusion Models2023 · IEEE/CVF International Conference on Computer Vision (ICCV) · 162 citationsWith Gordon Wetzstein, Miika Aittala, Shalini De Mello and Tero Karras
  3. CodedEvents: Optimal Point-Spread-Function Engineering for 3D-Tracking with Event Cameras2024 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 8 citations
  4. SUD²: Supervision by Denoising Diffusion Models for Image Reconstruction2023 · 2 citations
  5. Inverse synthetic aperture Fourier ptychography2026 · Optics Express · 1 citations

From OpenAlex, as of 21 October 2026.

  1. 16% of AI career moves in the 2020s went from a university to a companyIncludes Matthew Chan. 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 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 Matthew Chan yet. Send us a free-licensed photo.

  1. Matthew Chan | NVIDIA AI-Mediated Reality and Interaction Research research.nvidia.com. Checked 20 October 2026.
  2. Matthew Chan | LA ACM SIGGRAPH lasiggraph.org. Checked 20 October 2026.
  3. EG3D: Efficient Geometry-aware 3D GANs nvlabs.github.io. Checked 20 October 2026.
  4. Efficient Geometry-Aware 3D Generative Adversarial Networks | NVIDIA AI-Mediated Reality and Interaction Research research.nvidia.com. Checked 20 October 2026.
  5. Live 3D Portrait: Real-Time Radiance Fields for Single-Image Portrait View Synthesis research.nvidia.com. Checked 20 October 2026.
  6. AI-mediated 3D Video Conferencing (SIGGRAPH 2023 E-Tech Demo) research.nvidia.com. Checked 20 October 2026.
  7. Generative Novel View Synthesis with 3D-Aware Diffusion Models | NVIDIA AI-Mediated Reality and Interaction Research research.nvidia.com. Checked 20 October 2026.
  8. [2401.02411] What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs arxiv.org. Checked 20 October 2026.
  9. AI for Learning Photorealistic 3D Digital Humans from In-the-Wild Data | LA ACM SIGGRAPH lasiggraph.org. Checked 20 October 2026.
  10. Coherent 3D Portrait Video Reconstruction via Triplane Fusion research.nvidia.com. Checked 20 October 2026.
  11. GAIA: Generative Animatable Interactive Avatars with Expression-conditioned Gaussians research.nvidia.com. Checked 20 October 2026.
  12. Real-time 3D Visualization of Radiance Fields on Light Field Displays research.nvidia.com. Checked 20 October 2026.