Donglai Xiang

I am a Ph.D. student (Fall 2019 - now) at Robotics Institute, Carnegie Mellon University, advised by Prof. Jessica Hodgins. I obtained MS in Robotics at CMU in 2019, advised by Yaser Sheikh. Previously I obtained B. Eng. at Department of Electronic Engineering, Tsinghua University in 2017, advised by Prof. Liangrui Peng. I worked with Prof. Jia Deng at University of Michigan in 2016.

My research interests lie in Computer Vision, Computer Graphics and Machine Learning. My current research focus is on perception, analysis and generation of 3D data, especially for 3D human shape, pose and motion. I am managing the Panoptic Studio.

Email [xdl13thu at gmail dot com] - CV [updated Dec 2019]


Major Publications

You2Me: Inferring Body Pose in Egocentric Video via
First and Second Person Interactions

Evonne Ng, Donglai Xiang, Hanbyul Joo, Kristen Grauman
CVPR 2020 (Oral)
[arxiv] [project page]

Single-Network Whole-Body Pose Estimation
Gines Hidalgo, Yaadhav Raaj, Haroon Idrees, Donglai Xiang,
Hanbyul Joo, Tomas Simon, Yaser Sheikh
ICCV 2019

Monocular Total Capture: Posing Face, Body and Hands in the Wild
Donglai Xiang, Hanbyul Joo, Yaser Sheikh
CVPR 2019 (Oral)
[arxiv] [project page] [video]

Surface Normals in the Wild
Weifeng Chen, Donglai Xiang, Jia Deng
ICCV 2017
[arxiv] [project page]

Robust Text Detection with Vertically-Regressed Proposal Network
Donglai Xiang*, Qiang Guo*, Yan Xia
ECCV 2016 Workshop