Zachary Teed

I am a PhD student at Princeton University where I am advised by Jia Deng and a member of the Princeton Vision & Learning Lab. My current research focuses on 3D reconstruction from video; including Structure from Motion, Scene Flow, and SLAM. Previously, I graduated with a B.S in computer science from Washington University in St. Louis where I recieved the Langsdorf Fellowship and McKevely Research Award.

Email

profile photo
Research
PontTuset RAFT3D: Scene Flow using Rigid Motion Embeddings
Zachary Teed and Jia Deng
CVPR, 2021
paper / code (coming soon)

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

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

News

  • 08/2020: Our paper RAFT: Recurrent All-Pairs Field Transforms won best paper at ECCV 2020
  • 12/2019: Our paper DeepV2D: Video to Depth with Differentiable Structure from Motion was accepted to ICLR 2020
  • 04/2019: NSF Graduate Research Fellowship Honarable Mention
  • 10/2018: Oral Presentation at ALERT Conference
  • 01/2018: Kaggle Passenger Screening Algorithm Challenge 4th Place Solution

Template from here.