- This event has passed.
Fall 2023 GRASP Seminar: Yufei Ye, Carnegie Mellon University, “Predicting and Reconstructing Everyday Human Interactions”
December 12, 2023 at 1:15 PM - 2:15 PM
*This seminar will be held in-person in Levine 512 with virtual attendance via Zoom. The seminar will NOT be recorded.
ABSTRACT
In this talk, I will discuss about building computer vision system that understands everyday human interactions with rich spatial information, in particular hand-object interactions (HOI). Such systems can benefit VR/AR to perceive reality and to modify its virtual twin, and robotics to learn manipulation by watching humans. Previous methods are limited to constrained lab environments or pre-selected objects with known 3D shapes. My works explore learning general interaction priors from large-scale data that can generalize to novel everyday scenes for both perception and prediction.
The talk consists of two parts. The first part focuses on HOI prediction — predicting plausible human grasps for any objects. We found that image synthesis serves as a shortcut for 3D prediction for better generalization. The second part focuses on reconstructing interactions in 3D space for generic objects by leveraging data-driven prior, including from single images and everyday video clips.
Yufei Ye
Carnegie Mellon University
Yufei (Judy) Ye is a final year PhD student at CMU, working with Shubham Tulsiani and Abhinav Gupta. Prior to this, she obtained her B.E. in computer science from Tsinghua University, working with Prof. Shi-Min Hu. Her research interests generally lie at the intersection of computer vision, robotics, and machine learning. Her long-term goal is to build agents that can perceive everyday interactions for generic objects, understand the consequences of their own interactions with the physical world, and even hallucinate the potential effect had specific interactions occurred. Yufei has also interned in NVIDIA, Meta, and Yitu. She is selected as NVIDIA graduate fellow and EECS rising star workshop.