Towaki Takikawa

I am currently working on infrastructure software for deploying generative AI. It lets you manage models on a cache hierarchy, hot swap models instantly, minimize cold starts, scale horizontally, maintain version control, and secure models. If this sounds interesting, please reach out to towaki@outerport.com.

Until recently, I worked as a Research Scientist at NVIDIA Research on the Hyperscale Graphics Systems team with David Luebke.

I was also concurrently a Computer Science PhD student (on leave) at the University of Toronto, supervised by Sanja Fidler and Alec Jacobson, supported by the Borealis AI Fellowship.

My research interests broadly span computer graphics, computer vision, machine learning, and systems. In particular, I'm interested in distribution formats and infrastructure for visual content. In the past, I have worked on neural fields [1] and their combination with differentiable data structures [2,3,4] as a new compressed data format for immersive media (3D JPEG!).

Outside of research, I enjoy working on open source software for 3D machine learning (Kaolin Core, Kaolin Wisp). I generally enjoy straddling the line between research and engineering.

CV  /  Blog  /  LinkedIn  /  GitHub  /  Google Scholar  /  Twitter

Email:
tovacinni-at-gmail-dot-com

Experience
prl

Outerport
Co-Founder / CEO
July 2024 - Present

Model warehouse for fast AI deployments.
Reach out at towaki@outerport.com for more information.

prl

NVIDIA
Research Scientist
Toronto, ON, Canada
February, 2020 - November, 2023

Manager: Morgan McGuire, David Luebke
New Experiences Research Group, Hyperscale Graphics Systems.

Education

University of Toronto
Department of Computer Science
PhD Student
Computer Science
September 2020 - (on leave)
Supervisors: Sanja Fidler and Alec Jacobson

University of Waterloo
Faculty of Mathematics
Bachelor of Mathematics
Major in Computer Science
September, 2016 - May, 2020

Publications

Lagrangian Hashing for Compressed Neural Field Representations
Shrisudhan Govindarajan, Zeno Sambugaro, Ahan Shabhanov, Towaki Takikawa, Weiwei Sun, Daniel Rebain, Nicola Conci, Kwang Moo Yi, Andrea Tagliasacchi
European Conference on Computer Vision (ECCV), 2024
Project Website / Bibtex

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
Project Website / Bibtex

Compact Neural Graphics Primitives with Learned Hash Probing
Towaki Takikawa, Thomas Müller, Merlin Nimier-David, Alex Evans, Sanja Fidler, Alec Jacobson, Alexander Keller
SIGGRAPH Asia, 2023
Project Website / Bibtex

ATT3D: Amortized Text-To-3D Object Synthesis
Jonathan Lorraine, Kevin Xie, Xiaohui Zeng, Chen-Hsuan Lin, Towaki Takikawa, Nicholas Sharp, Tsung-Yi Lin, Ming-Yu Liu, Sanja Fidler, James Lucas
International Conference on Computer Vision (ICCV), 2023
Project Website / Bibtex

Magic3D: High-Resolution Text-to-3D Content Creation
Chen-Hsuan Lin*, Jun Gao*, Luming Tang*, Towaki Takikawa*, Xiaohui Zeng*, Xun Huang, Karsten Kreis, Sanja Fidler, Ming-Yu Liu, Tsung-Yi Lin
Computer Vision and Pattern Recognition (CVPR), 2023
Highlight (Top 2%)
Project Website / Bibtex

Variable Bitrate Neural Fields
Towaki Takikawa, Alex Evans, Jonathan Tremblay, Thomas Müller, Morgan McGuire, Alec Jacobson, Sanja Fidler
SIGGRAPH North America, 2022
Project Website / Code / Bibtex

A Dataset and Explorer for 3D Signed Distance Functions
Towaki Takikawa, Andrew Glassner, Morgan McGuire
Journal of Computer Graphics Techniques (JCGT / i3D), 2022
Project Website / Code / Bibtex

Neural Fields in Visual Computing and Beyond
Yiheng Xie, Towaki Takikawa, Shunsuke Saito, Or Litany, Shiqin Yan, Numair Khan, Federico Tombari, James Tompkin, Vincent Sitzmann, Srinath Sridhar
Eurographics / Computer Graphics Forum (EG / CGF), 2022
State of the Art Report (STAR)
Project Website / Bibtex

RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis
Jonathan Tremblay, Moustafa Meshry, Alex Evans, Jan Kautz, Alexander Keller, Sameh Khamis, Charles Loop, Nathan Morrical, Thomas Müller, Koki Nagano, Towaki Takikawa, Stan Birchfield
Tech Report, 2022
Project Website / Bibtex

Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes
Towaki Takikawa*, Joey Litalien*, Kangxue Yin, Karsten Kreis, Charles Loop, Derek Nowrouzezahrai, Alec Jacobson, Morgan McGuire, Sanja Fidler
Computer Vision and Pattern Recognition (CVPR), 2021
Oral Presentation (Top 4%)
Project Website / Code / Video / Bibtex

Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
Towaki Takikawa*, David Acuna*, Varun Jampani, Sanja Fidler
International Conference on Computer Vision (ICCV), 2019
Project Website / Code / Bibtex

Internships
prl

WATonomous
Software Director / Mentor
Waterloo, ON, Canada
May, 2017 - May, 2020

Helping the team engineer a fully autonomous Cheverolet Bolt.
Certified by GM as a designated test driver.
Working across the pipeline on perception, prediction, localization, planning.
Managing over 100+ students and 6 different software subteams.

prl

Preferred Networks
Research Intern
Tokyo, Japan
May, 2019 - August, 2019

Mentor: Richard Calland, Tommi Kerola
Research on weakly-supervised instance segmentation.

prl

NVIDIA
Research Intern
Toronto, ON, Canada
January, 2019 - April, 2019

Mentor: David Acuna, Sanja Fidler
Research on representation learning for semantic segmentation.

prl

University of Waterloo
Research Assistant
Waterloo, ON, Canada
September, 2018 - May, 2020

Mentor: Yuri Boykov
Research on weakly-supervised semantic segmentation and domain adaptation.

prl

NVIDIA
Systems Software Engineering Intern
Santa Clara, CA, USA
May, 2018 - August, 2018

Worked in the autonomous vehicles engineering team.
Developed data labeling and data recording systems in C / C++.
Performed hardware verification and validation in the lab.
Helped architect a hardware-based sensor synchronization system.

prl

Tulip Interfaces
Software Engineering Intern
Somerville, MA, USA
May, 2017 - August, 2017

Worked on software infrastructure and internal tools.

prl

Active911
Software Engineering Intern
Philomath, OR, USA
June, 2016 - August, 2016

Worked on software infrastructure and backend development.

prl

Linn Benton Community College
Software Engineering Intern
Corvallis, OR, USA
June, 2015 - August, 2015

Worked on curriculum development for an introductory CS course.

prl

Oregon State University
Research Intern
Corvallis, OR, USA
June, 2014 - August, 2014

Mentor: Alex Groce
Research in automated software verification and validation.

Portofolio
Neural Fluid Fields
Neural Navier-Stokes!
Retrowave GLSL
Tweet GLSL Demo
WATonomous
Self-driving in 3 years
CommuniWAT
HCI Final Project
Cool Pen
Lathed from aluminum
Crystal Mayhem
Scholastic Gold Key Award
Violin Concerto
My Last Concerto
Custom Gearbox
6 CIM Anodized
Quaternion Blast
CodeDay Portland 2015
Elevator Bot
FRC 2015/PNW Champs
Zipper
FRC 2014
Frisber
FRC 2013
Art (?)

Template: Jon Barron and Morgan McGuire