Zachary Teed

I worked as an autonomy engineer at Skydio from 2022 to 2024.

I graduated with a PhD in computer science from Princeton University in 2022. I was advised by Jia Deng and a member of the Princeton Vision and Learning Lab. My work focuses on combining multiview geometry with deep learning. Some of my favorite topics include optical flow and simultaneous localization and mapping (SLAM).

In 2022, I placed 2nd in the US Beer Mile National Championships and went on to compete in the World Championships.

zachteed[at]gmail[dot]com

profile photo
Research
PontTuset DPVO: Deep Patch Visual Odometry
Zachary Teed*, Lahav Lipson*, and Jia Deng
NeurIPS, 2023
paper / code

PontTuset DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras
Zachary Teed and Jia Deng
NeurIPS, 2021
paper / code

PontTuset RAFT3D: Scene Flow using Rigid Motion Embeddings
Zachary Teed and Jia Deng
CVPR, 2021
paper / code

PontTuset Tangent Space Backpropogation for 3D Transformation Groups
Zachary Teed and Jia Deng
CVPR, 2021
paper / code

PontTuset RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
Zachary Teed and Jia Deng
ECCV 2020 Best Paper Award
paper / code

PontTuset DeepV2D: Video to Depth with Differentiable Structure from Motion
Zachary Teed and Jia Deng
ICLR, 2020
paper / code

PontTuset A computationally efficient algorithm for fitting ion channel parameters
Zachary Teed and Jonathan Silva
MethodsX, 2016
code

Template from here.