Hello, I'm Keunhong Park

I am a Ph. D student at the University of Washington with Ali Farhadi and Steve Seitz.

I work at the intersection of computer vision and computer graphics. I have worked on automatically translating 2D representations (images) into more dynamic representations (geometry and appearance). I am currently exploring ways to leverage multi-modal data for scene understanding.


  • November 2020: We present Nerfies, a way to turn casually captured selfie videos into free-viewpoint visualizations!
  • June 2020: We've released the code and data for LatentFusion. We will be presenting at CVPR 2020--see you there!
  • February 2020: Our paper on zero-shot pose estimation has been accepted to CVPR 2020.