Loading Events

« All Events

  • This event has passed.

Fall 2023 GRASP Seminar: Donglai Xiang, Carnegie Mellon University, “Modeling Dynamic Clothing for Data-Driven Photorealistic Avatars”

October 17, 2023 at 1:30 PM - 2:30 PM

This is a hybrid event with in-person attendance in Levine 512 and virtual attendance on Zoom.

ABSTRACT

In this talk, I will present research on building photorealistic avatars of humans wearing complex clothing in a data-driven manner. Such avatars will be a critical technology to enable future applications such as VR/AR and virtual content creation. Loose-fitting clothing poses a significant challenge for avatar modeling due to its large deformation space. We address the challenge by unifying three components of avatar modeling: model-based statistical prior from pre-captured data, physics-based prior from simulation, and real-time measurement from sparse sensor input. First, we introduce a separate two-layer representation that allows us to disentangle the dynamics between the pose-driven body part and temporally-dependent clothing part. Second, we further combine physics-based cloth simulation with a physics-inspired neural rendering model to generate rich and natural dynamics and appearance even for challenging clothing such as a skirt and a dress. Last, we go beyond pose-driven animation and incorporate online sensor input into the avatars to achieve more faithful telepresence of clothing.

Donglai Xiang

Carnegie Mellon University

Donglai Xiang is a Ph.D. candidate at Robotics Institute at Carnegie Mellon University. His research focuses on modeling photorealistic dynamic humans, especially the tracking, rendering, and animation of clothing. He is broadly interested in various topics in computer graphics and vision, including but not limited to learning, geometry processing, and simulation. He won a best paper honorable mention award at 3DV 2020, and outstanding reviewer recognition at CVPR/ICCV. He was a visiting researcher and intern at Meta Reality Labs Pittsburgh from 2021 to 2023. He obtained an M.S. degree from CMU in 2019 and a B. Eng. from Tsinghua University in 2017.

Details

Date:
October 17, 2023
Time:
1:30 PM - 2:30 PM
Event Category:
Website:
https://www.grasp.upenn.edu/events/fall-2023-grasp-seminar-donglai-xiang/

Organizer

General Robotics, Automation, Sensing and Perception (GRASP) Lab
Email
grasplab@seas.upenn.edu
View Organizer Website

Venue

Levine 512