Keunhong Park

Ph.D Student

A portrait of Keunhong Park

Education

University of Washington
Ph. D in Computer Science, advised by Steven M. Seitz and Ali Farhadi.
Supported by Samsung Scholarship 2015-2020 ($50,000/year for 5 years)
Fall 2015 - (current)
University of Illinois at Urbana-Champaign
B.S. in Computer Science, advised by Derek Hoiem.
Fall 2009 - Spring 2013

Employment

Google
Research Intern on the Project Starline team. Worked on Nerfies and HyperNeRF.
Jun 2020 - Sep 2021
NVIDIA
Robotics Research Intern at the Seattle Robotics Lab. Worked on LatentFusion.
Jul 2019 - Nov 2020
Amazon
Applied Scientist Intern on the Amazon Go team. Worked on human activity detection.
Jul 2017 - Sep 2017
Ministry of National Defense, Cyber Command
Software Engineer (mandatory military service). Worked on network monitoring software.
Oct 2013 - Jul 2015
Google
Software Engineering Intern. Create document conversion system for Google Cloud Print.
May 2013 - Aug 2013
Qualcomm
Software Engineering Intern. Optimized performance of JGit, reducing push times from hours to seconds. Implemented multi-master support for Gerrit Code Review.
May 2012 - Aug 2012

Publications

HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields By applying ideas from level set methods, we can represent topologically changing scenes with NeRFs.
arXiv, 2021
FiG-NeRF: Figure Ground Neural Radiance Fields for 3D Object Category Modelling
Given a lot of images of an object category, you can train a NeRF to render them from novel views and interpolate between different instances.
arXiv, 2021
Nerfies: Deformable Neural Radiance Fields
Learning deformation fields with a NeRF let's you reconstruct non-rigid scenes with high fidelity.
arXiv, 2020
LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation
By learning to predict geometry from images, you can do zero-shot pose estimation with a single network.
CVPR, 2020
PhotoShape: Photorealistic Materials for Large-Scale Shape Collections
By pairing large collections of images, 3D models, and materials, you can create thousands of photorealistic 3D models fully automatically.
SIGGRAPH Asia, 2018