PeopleofSuperintelligence

Researcher

Alex Trevithick

Alex Trevithick is a research scientist at NVIDIA, where he works on computer vision, generative models and machine learning. He studied mathematics and computer science at Williams College, earned a computer-science PhD at UC San Diego, and developed robust view-synthesis methods at Google DeepMind. His work includes GRF, real-time 3D portraits and SimVS, which uses generative video models to handle inconsistent scene captures. In 2026, he coauthored Grounded-Exo2Ego, a video diffusion model that uses semantic grounding to generate egocentric video from exocentric footage.

Now at
NVIDIA
Works
18
Citations
449
h-index
7
Badges

Publication numbers from OpenAlex, as of 18 October 2026.

Timeline

  1. 2019

    Wearable computing research

    In 2019, as a Williams junior, he takes part in Washington State University's NSF-sponsored wearable-computing REU. He uses a brain-computer interface whose software learns how his electrical brain signals change with his facial expressions.

  2. 2021

    General radiance fields

    He studies mathematics and computer science at Williams College, graduating in 2021. With Bo Yang, he publishes GRF at ICCV; its per-pixel features help NeRF generalize to new scenes without retraining.

  3. 2022

    An NSF fellowship

    In May 2022, he joins three other UC San Diego CSE students as an NSF Research Fellow.

  4. 2023

    Portraits from one image

    During two NVIDIA internships, he develops algorithms for generative modeling and single-image human view synthesis. In 2023, he coauthors Live 3D Portrait, which renders a photorealistic 3D representation from one unposed portrait in real time.

  5. 2024

    Simulating inconsistent scenes

    At Google DeepMind, he develops methods for robust view synthesis and 4D reconstruction using data generated by video models. In 2024, he coauthors SimVS, which uses generative video models to simulate inconsistencies in captured scenes and train a harmonization network to reconcile them into a consistent 3D scene.

  6. Since 2025

    Research Scientist at NVIDIA

    In 2025, he earns a computer-science PhD at UC San Diego and joins NVIDIA Research as a research scientist. His research interests span computer vision, generative models and machine learning. In 2026, he coauthors Grounded-Exo2Ego, a dual-branch video diffusion model that uses semantic grounding to generate egocentric video from a single exocentric video.

A language model matched the links in this timeline to people, organizations and papers (provisional, model-judged).

Career

  1. Since 2025NVIDIAIntern
  2. 2025Google DeepMind

Education

  1. 2025University of California, San DiegoPhD
  2. 2021Williams CollegeMathematics 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. GRF: Learning a General Radiance Field for 3D Representation and Rendering2021 · IEEE/CVF International Conference on Computer Vision (ICCV) · 202 citations
  2. Real-Time Radiance Fields for Single-Image Portrait View Synthesis2023 · ACM Transactions on Graphics · 71 citationsWith Ravi Ramamoorthi
  3. GRF: Learning a General Radiance Field for 3D Scene Representation and Rendering2021 · International Conference on Computer Vision · 48 citations
  4. CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models2025 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 37 citationsWith Jonathan T. Barron
  5. NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion2023 · 36 citationsWith Christian Theobalt and Ravi Ramamoorthi

From OpenAlex, as of 18 October 2026.

  1. Of 410 people shaping AI who worked at Google, 161 work there nowIncludes Alex Trevithick. Our estimates of where former Google and Google DeepMind people work now, including moves within Google.
  2. 13% of AI career moves in the 2020s went from a university to a companyIncludes Alex Trevithick. Our estimates of how university-to-company career transitions changed by decade, including roles added alongside an earlier job.
  3. The median h-index is 55 at universities and 20 at frontier AI labsIncludes Alex Trevithick. The median h-index is 55 at universities and 20 at frontier AI labs. We compare publishing careers, citations and moves to estimate how universities and frontier labs contribute to AI research.
  4. Google alumni founded or led 79 other organizations, the most among the labs we compareIncludes NVIDIA. We trace 181 organizations founded or led by AI lab alumni, and 187 career moves between the labs.

Colleagues

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

Sources and credits

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

  1. Crafting Caring Spaces vcea.wsu.edu. Checked 18 October 2026.
  2. Alex Trevithick | NVIDIA AI-Mediated Reality and Interaction Research research.nvidia.com. Checked 18 October 2026.
  3. Alex Trevithick alextrevithick.com. Checked 18 October 2026.
  4. CSE’s NSF PhD Research Fellows cns.ucsd.edu. Checked 18 October 2026.
  5. Real-Time Radiance Fields for Single-Image Portrait View Synthesis arxiv.org. Checked 18 October 2026.
  6. SimVS: Simulating World Inconsistencies for Robust View Synthesis arxiv.org. Checked 18 October 2026.
  7. Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation arxiv.org. Checked 18 October 2026.