Donglai XiangI 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 |
PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
|
|
Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration
|
|
Drivable Avatar Clothing: Faithful Full-Body Telepresence |
|
Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing
|
|
Pattern-Based Cloth Registration and Sparse-View Animation
|
|
Modeling Clothing as a Separate Layer for an Animatable Human Avatar
|
|
Revitalizing Optimization for 3D Human Pose and Shape Estimation: |
|
MonoClothCap: Towards Temporally Coherent Clothing Capture |
|
You2Me: Inferring Body Pose in Egocentric Video via |
|
Single-Network Whole-Body Pose Estimation
|
|
Monocular Total Capture: Posing Face, Body and Hands in the Wild
|
|
Surface Normals in the Wild
|
|
Robust Text Detection with Vertically-Regressed Proposal Network
|