Alex Trevithick

About Me

Research Scientist

NVIDIA Research

Education

Ph.D. Computer Science

UC San Diego

Advisor

Prof. Ravi Ramamoorthi

Hello, I'm Alex

I'm an incoming Research Scientist at NVIDIA after finishing my Ph.D. at UC San Diego, advised by Professor Ravi Ramamoorthi and supported by the NSF Graduate Research Fellowship.

Reach out if you're interested in collaborating!

Research Interests

I'm interested in training and leveraging generative models for computer vision, especially pushing towards 4D reconstruction, real-time inference, and photorealistic generation.

See my research

Research

I'm interested in training and leveraging generative models for computer vision, especially pushing towards 4D reconstruction, real-time inference, and photorealistic generation.

SimVS: Simulating World Inconsistencies for Robust View Synthesis

Alex Trevithick, Roni Paiss, Philipp Henzler, Dor Verbin, Rundi Wu, Hadi Alzayer, Ruiqi Gao, Ben Poole, Jonathan T. Barron, Aleksander Holynski, Ravi Ramamoorthi, Pratul P. Srinivasan

Computer Vision and Pattern Recognition (CVPR), 2025

Turn inconsistent captures into consistent multiview images through simulation with video models.

Project Page Paper

CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models

Rundi Wu, Ruiqi Gao, Ben Poole, Alex Trevithick, Changxi Zheng, Jonathan T. Barron, Aleksander Holynski

Computer Vision and Pattern Recognition (CVPR), 2025

Sample 4D scenes from text, video, or sparse images.

Project Page Paper

RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion

Jaidev Shriram*, Alex Trevithick*, Lingjie Liu, Ravi Ramamoorthi

International Conference on 3D Vision (3DV), 2025

Sample 3D scenes from text with diffusion.

Project Page Paper Code

What You See Is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

Alex Trevithick, Matthew Chan, Towaki Takikawa, Umar Iqbal, Shalini De Mello, Manmohan Chandraker, Ravi Ramamoorthi, Koki Nagano

Computer Vision and Pattern Recognition (CVPR), 2024

Photorealistic geometry in 3D generative models by rendering every pixel.

Project Page Paper

AI-mediated 3D Videoconferencing

Michael Stengel, Koki Nagano, Chao Liu, Matthew Chan, Alex Trevithick, Shalini De Mello, Jonghyun Kim, David Luebke, Amrita Mazumdar, Shengze Wang, Mayoore Jaiswal

SIGGRAPH Emerging Technologies, 2023

Real-time demo for immersive 3D videoconferencing built with Live 3D Portrait.

Project Page Paper

Real-Time Radiance Fields for Single-Image Portrait View Synthesis

Alex Trevithick, Matthew Chan, Michael Stengel, Eric R. Chan, Chao Liu, Zhiding Yu, Sameh Khamis, Manmohan Chandraker, Ravi Ramamoorthi, Koki Nagano

ACM Transactions on Graphics (SIGGRAPH), 2023

Real-time encoding and view synthesis from a single portrait image learned with strictly synthetic data.

Project Page Paper Two Minute Papers

NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion

Jiatao Gu, Alex Trevithick, Kai-En Lin, Josh Susskind, Christian Theobalt, Lingjie Liu, Ravi Ramamoorthi

International Conference on Machine Learning (ICML), 2023

Distill the knowledge of a 3D-aware conditional diffusion model into a triplane NeRF.

Project Page Paper

PVP: Personalized Video Prior for Editable Dynamic Portraits using StyleGAN

Kai-En Lin, Alex Trevithick, Keli Chang, Michel Sarkis, Mohsen Ghafoorian, Ning Bi, Gerhard Reitmayr, Ravi Ramamoorthi

Computer Graphics Forum (EGSR), 2023

Leverage the StyleGAN latent space for multi view consistent edits in real-time.

Project Page Paper

GRF: Learning a General Radiance Field for 3D Scene Representation and Rendering

Alex Trevithick, Bo Yang

International Conference on Computer Vision (ICCV), 2021

Per-pixel features improve NeRF and allow it to generalize to new scenes without retraining.

Paper Code Video

Hello, I'm

Alex Trevithick

About Me

Hello, I'm Alex

Research Interests

Research

SimVS: Simulating World Inconsistencies for Robust View Synthesis

CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models

RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion

What You See Is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

AI-mediated 3D Videoconferencing

Real-Time Radiance Fields for Single-Image Portrait View Synthesis

NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion

PVP: Personalized Video Prior for Editable Dynamic Portraits using StyleGAN

GRF: Learning a General Radiance Field for 3D Scene Representation and Rendering

Media Coverage

NVIDIA CEO Jensen Huang Presents Our Work at Computex 2023

Two Minute Papers Features Live 3D Portrait

Experience

Research Scientist

Student Researcher

Research Intern (2x)

Visiting Researcher

Wilmers Fellow