About

I'm a Ph.D. student (2017-) at Robotics Institute, Carnegie Mellon University, advised by Prof.  Kris Kitani. My research lies at the intersection of computer vision, machine learning and computer graphics. I’m interested in leveraging physics in the visual reasoning of human behaviors, especially 3D pose estimation, taking inspirations from recent advances in character control, reinforcement learning and imitation learning.  I also finished my M.S. in computer science at CMU in 2016, where I worked with Prof. Stelian Coros on computational fabrication, motion planning and computer animation. I obtained my B.E. in computer science and technology from Zhejiang University in 2015.

News

  • [2018-07-03] Paper 3D Ego-Pose Estimation via Imitation Learning accepted to ECCV 2018.

  • [2018-06-10] Paper Computational Design of Transformables accepted to SCA 2018.

  • [2018-05-21] Starting my internship at Oculus Research Pittsburgh.

Publications

Diverse Trajectory Forecasting with Determinantal Point Processes
Ye Yuan, Kris Kitani
arXiv preprint, 2019
paper video
Ego-Pose Estimation and Forecasting as Real-Time PD Control
Ye Yuan, Kris Kitani
arXiv preprint, 2019
paper video
Generative Hybrid Representations for Activity Forecasting with No-Regret Learning
Jiaqi Guan, Ye Yuan, Kris Kitani, Nick Rhinehart
arXiv preprint, 2019
paper
3D Ego-Pose Estimation via Imitation Learning
Ye Yuan, Kris Kitani
European Conference on Computer Vision (ECCV), 2018
paper video poster
Computational Design of Transformables
Ye Yuan, Changxi Zheng, Stelian Coros
ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA), 2018
paper video slides
Computational Abstractions for Interactive Design of Robotic Devices
Ruta Desai, Ye Yuan, Stelian Coros
IEEE International Conference on Robotics and Automation (ICRA), 2017
paper video
Continuous Optimization of Interior Carving in 3D Fabrication
Yue Xie, Ye Yuan, Xiang Chen, Changxi Zheng, Kun Zhou
Frontiers of Computer Science, 2016
paper