Weifeng Chen

I am an applied scientist at the Rekognition Team @ AWS. I did my Ph.D. at the University of Michigan, Ann Arbor, where I was advised by Prof. Jia Deng. Previously, I received my B. Eng degree from Zhejiang University under the supervision of Prof. Guofeng Zhang. I spent the last two years of my Ph.D. at the Princeton Vision & Learning Lab.

My research interests lie in computer vision and machine learning. I am especially interested in research on inferring shapes, motions, and physics from images and videos.

wfchen@umich.edu  /  Google Scholar  /  Github

Publications
Humble Teachers Teach Better Students for Semi-supervised Object Detection
Yihe Tang, Weifeng Chen, Yijun Luo, Yuting Zhang
Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[paper]

We propose a semi-supervised approach for contemporary object detectors following the teacher-student dual model framework.

Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control
Yu-Wei Chao, Jimei Yang, Weifeng Chen, Jia Deng
AAAI Conference on Artificial Intelligence (AAAI), 2021.
[paper][video]

We propose a hierarchical reinforcement framework to learn high-level interactive tasks.

OASIS: A Large-Scale Dataset for Single Image 3D in the Wild
Weifeng Chen, Shengyi Qian, David Fan, Noriyuki Kojima, Max Hamilton, Jia Deng
Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
[paper][supplementary material][project site]

We present Open Annotations of Single Image Surfaces (OASIS), a dataset consisting of detailed 3D geometry for images in the wild.

Learning Single-Image Depth from Videos using Quality Assessment Networks
Weifeng Chen, Shengyi Qian, Jia Deng
Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[paper][project site][code]

We propose a method to automatically generate training data for single-view depth through Structure-from-Motion (SfM) on Internet videos.

Surface Normals in the Wild
Weifeng Chen, Donglai Xiang, Jia Deng
International Conference on Computer Vision (ICCV), 2017.
[paper][dataset][code]
Invited [poster] at the Bridges to 3D Workshop, CVPR 2018

We present a new dataset "Surface Normals in the Wild" consisting of images in the wild annotated with surface normals of random points.

Single-Image Depth Perception in the Wild
Weifeng Chen, Zhao Fu, Dawei Yang, Jia Deng
Neural Information Processing Systems (NeurIPS), 2016.
[paper][dataset][code][supplementary material][BibTex]

We introduce a new dataset "Depth in the Wild" consisting of images in the wild annotated with relative depth between pairs of random points.

Featured in the Wolfram Neural Net Repository. See this article for more details.
Multi-Viewpoint Panorama Construction with Wide-Baseline Images
Guofeng Zhang, Yi He, Weifeng Chen, Jiaya Jia and Hujun Bao
IEEE Transactions on Image Processing (TIP), 2016.
[paper]

We design a mesh-based framework for creating panoramas from wide-baseline images.

High-Quality Depth Recovery via Interactive Multi-View Stereo
Weifeng Chen, Guofeng Zhang, Xiaojun Xiang, Jiaya Jia and Hujun Bao
International Conference on 3D Vision (3DV), 2014.
[paper]

We align CAD models interactively to fix artifacts in MVS output.

Service

Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, SIGGRAPH Asia, ICRA, AAAI, WACV, ACCV

Template Credit: Jon Barron