Zhichao Yin

I was a full-time researcher at Berkeley DeepDrive, where I worked on computer vision and deep learning with Fisher Yu and Trevor Darrell. My research interests focus on integrating deep learning techniques into geometry understanding and motion analysis of general images or videos. I have also collaborated with Jianping Shi at SenseTime Research. I did my bachelors in Mathematics at Fudan University.

E-mail  /  Google Scholar  /  Github

Research
HD3

Hierarchical Discrete Distribution Decomposition for Match Density Estimation
Zhichao Yin, Trevor Darrell, Fisher Yu
Computer Vision and Pattern Recognition (CVPR), 2019

Paper  /  Code  /  Bibtex 
@inproceedings{yin2019hd3,
title = {Hierarchical Discrete Distribution Decomposition
for Match Density Estimation},
author = {Yin, Zhichao and Darrell, Trevor and Yu,
Fisher},
booktitle = {CVPR},
year = {2019}
}

We propose Hierarchical Discrete Distribution Decomposition (HD3), a framework suitable for learning probabilistic pixel correspondences. Our method achieves state-of-the-art results on both KITTI Stereo & Flow Benchmarks (rank the 1st in optical flow).

GeoNet

GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
Zhichao Yin, Jianping Shi
Computer Vision and Pattern Recognition (CVPR), 2018

Paper  /  Code  /  Bibtex 
@inproceedings{yin2018geonet,
  title     = {GeoNet: Unsupervised Learning of Dense Depth,
              Optical Flow and Camera Pose},
  author    = {Yin, Zhichao and Shi, Jianping},
  booktitle = {CVPR},
  year = {2018}
}

We propose GeoNet, a jointly unsupervised learning framework for monocular depth, optical flow and ego-motion estimation from videos.


Template: this