Frank Yu

I am a first year M.Sc. student in Computer Science at the University of British Columbia (UBC), where I am supervised by Prof. Helge Rhodin.

Previously, I have completed my B.Sc. in Electrical Engineering at the University of Manitoba, where I was also an undergraduate research assistant in Prof. Yang Wang's Lab.

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn  /  Twitter  /  Instagram

profile photo
News

  New! March 2021: PCL Paper accepted to CVPR 2021 (Poster)
  New! January 2021: A-NeRF paper available on arxiv
  November 2020: I will be a student volunteer at NeurIPS 2020
  September 2020: Starting my M.Sc in Computer Science at the University of British Columbia
  August 2020: Paper accepted to ECCV 2020 (Spotlight)
  June 2020: Graduated from the University of Manitoba with a B.Sc in Electrical Engineering

Research

I'm interested in computer vision and machine learning. I am currently conducting research on 3D vision and 3D human pose estimation.

profile photo New!A-NeRF: Surface-free Human 3D Pose Refinement via Neural Rendering
Shih-Yang Su, Frank Yu, Michael Zollhoefer, Helge Rhodin,
arXiv Preprint
Paper | Project Page

We present an analysis-by-synthesis approach for monocular motion capture that learns a volumetric body model and refines the 3D pose estimation of the user in a self-supervised manner.

profile photo New! PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers
Frank Yu, Mathieu Salzmann, Pascal Fua, Helge Rhodin,
CVPR 2021 (Poster)
Paper

We propose PCL (perspective crop layer), a set of modular neural network layers that when inserted into MLPs or CNNs will deterministically remove location-dependent perspective effects leading to more precise 3D human pose estimation.

profile photo Few-shot Scene-adaptive Anomaly Detection
Yiwei Lu, Frank Yu, Mahesh Kumar Krishna Reddy, Yang Wang
ECCV 2020 (Spotlight)
Paper | Code

We propose a more realistic problem setting for anomaly detection in surveillance videos and solve it using a meta-learning based algorithm.


Credits to Jon Barron for the website design.