Shaowei Liu

I’m a CS PhD student at the University of Illinois Urbana-Champaign, being advised by Prof. Saurabh Gupta and Prof. Shenlong Wang.

I received my master's degree in Computer Science from UCSD, advised by Prof. Xiaolong Wang. Before that, I received my bachelor’s degree in Electrical Engineering from Tsinghua University.

My research interests lie in computer vision and robotics. I am interested in 3D vision, video understanding and the intersection of vision and robotics.

Google Scholar  /  Github  /  Twitter

profile photo

Email: shaowei3@illinois.edu

Publications
Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos
Shaowei Liu, Subarna Tripathi, Somdeb Majumdar, Xiaolong Wang
Conference on Computer Vision and Pattern Recognition (CVPR) 2022
Paper Project Code

We propose to forecast future hand-object interactions given an egocentric video.

DexMV: Imitation Learning for Dexterous Manipulation from Human Videos
Yuzhe Qin*, Yueh-Hua Wu*, Shaowei Liu, Hanwen Jiang, Ruihan Yang, Yang Fu, Xiaolong Wang
European Conference on Computer Vision (ECCV) 2022
Paper Project Code

we propose a new platform and pipeline, DexMV (Dexterous Manipulation from Videos), for imitation learning to bridge the gap between computer vision and robot learning.

Hand-Object Contact Consistency Reasoning for Human Grasps Generation
Hanwen Jiang* Shaowei Liu*, Jiashun Wang and Xiaolong Wang
International Conference on Computer Vision (ICCV) 2021 Oral
Paper Project Code

We propose to generate human grasps given a 3D object in the world based on the hand-object contact consistency.

Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time
Shaowei Liu*, Hanwen Jiang*, Jiarui Xu, Sifei Liu and Xiaolong Wang
Conference on Computer Vision and Pattern Recognition (CVPR) 2021
Paper Project Code

We build a joint learning framework for estimating the 3D hand and object poses by leveraging the spatial-temporal consistency in large-scale hand-object videos.

Light and Fast Hand Pose Estimation From Spatial-Decomposed Latent Heatmap
Shaowei Liu, Guijin Wang, Pengwei Xie, Cairong Zhang
IEEE Access 2020
Paper Bibtex

We present a light and efficient approach for fast and accurate hand pose estimation from a single depth image.

Experiences

Intel AI Lab
Multimodal Learning Intern
Jun. 21 - Aug. 21

Noah's Ark Lab
Assistant Research Engineer
July. 18 - Oct. 18

Baidu IDL
Computer Vision Engineer
July. 17 - Sep. 17

Award
    Outstanding Undergraduate Thesis (Top 5%), Tsinghua University. 2019