Donglai Xiang

I am a research scientist at Nvidia Research. My current research focuses on dynamic 3D modeling, generation and reconstruction. I am broadly interested in various topics in computer graphics and vision, including but not limited to learning, geometry, and simulation, and appearance modeling.

I obtained my Ph.D. (2023) and M.S. (2019) from Robotics Institute, Carnegie Mellon University, advised by Prof. Jessica Hodgins and Prof. Yaser Sheikh. During my Ph.D. I collaborated extensively with Meta Reality Labs Research in Pittsburgh as a visiting researcher. Previously I obtained a B. Eng. in Electronic Engineering at Tsinghua University, Beijing in 2017. I worked with Prof. Jia Deng at University of Michigan in 2016.

Email [xdl13thu at gmail dot com] · CV [updated Jul 2024] · Google Scholar

News

Selected Publications

PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
Yang Zheng, Qingqing Zhao, Guandao Yang, Wang Yifan, Donglai Xiang, Florian Dubost,
Dmitry Lagun, Thabo Beeler, Federico Tombari, Leonidas Guibas, Gordon Wetzstein
ECCV 2024
[project page] [arXiv]

Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration
Jingfan Guo, Fabian Prada, Donglai Xiang, Javier Romero, Chenglei Wu,
Hyun Soo Park, Takaaki Shiratori, Shunsuke Saito
3DV 2024
[project page] [arXiv]

Drivable Avatar Clothing: Faithful Full-Body Telepresence
with Dynamic Clothing Driven by Sparse RGB-D Input

Donglai Xiang, Fabian Prada, Zhe Cao, Kaiwen Guo,
Chenglei Wu, Jessica Hodgins, Timur Bagautdinov
SIGGRAPH Asia 2023
[arXiv] [project page]

Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing
Donglai Xiang, Timur Bagautdinov, Tuur Stuyck, Fabian Prada, Javier Romero,
Weipeng Xu, Shunsuke Saito, Jingfan Guo, Breannan Smith, Takaaki Shiratori,
Yaser Sheikh, Jessica Hodgins, Chenglei Wu
ACM Transaction on Graphics (SIGGRAPH Asia 2022)
[arXiv] [video] [ACM DL] Media Coverage [UploadVR] [80 Level] [Mogura VR]

Pattern-Based Cloth Registration and Sparse-View Animation
Oshri Halimi, Tuur Stuyck, Donglai Xiang, Timur Bagautdinov, He Wen, Ron Kimmel,
Takaaki Shiratori, Chenglei Wu, Yaser Sheikh, and Fabian Prada
ACM Transaction on Graphics (SIGGRAPH Asia 2022)
[arXiv]

Modeling Clothing as a Separate Layer for an Animatable Human Avatar
Donglai Xiang, Fabian Prada, Timur Bagautdinov, Weipeng Xu,
Yuan Dong, He Wen, Jessica Hodgins, Chenglei Wu
ACM Transaction on Graphics (SIGGRAPH Asia 2021)
[Open Access] [arXiv] [video] [supplementary document]

Revitalizing Optimization for 3D Human Pose and Shape Estimation:
A Sparse Constrained Formulation

Taosha Fan, Kalyan Vasudev Alwala, Donglai Xiang,
Weipeng Xu, Todd Murphey, Mustafa Mukadam
ICCV 2021
[arXiv] [Project Page]

MonoClothCap: Towards Temporally Coherent Clothing Capture
from Monocular RGB Video

Donglai Xiang, Fabian Prada, Chenglei Wu, Jessica Hodgins
3DV 2020 (Best Paper Honorable Mention, Oral)
[arXiv] [video]

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
[arXiv]

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
[paper]

Experiences

MISC