Ziyun (Claude) Wang

I'm a Ph.D. student at the GRASP Laboratory at the University of Pennsylvania. I'm advised by Professor Kostas Daniilidis. I received my B.S. in Computer Science from Rice University and M.S.E in Robotics from Penn. Previously, I was a research intern at Samsung AI Center New York, where I worked with Professors Sebastian Seung, Daniel Lee, and Volkan Isler. I did my most recent internship at the Apple Vision Product team, working on the Vision Pro.

Email  /  CV  /  ScholarX  

profile photo

News & Updates

  • [08/23/2024] I finished my internship with the Vision Product Group at Apple.
  • [07/03/2024] Four papers accepted to ECCV 2024. See you in Milan!
  • [06/18/2023] Our new dataset M3ED is presented at the CVPR event vision workshop.
  • [07/12/2022] "EV-Catcher: High-Speed Object Catching Using Low-latency Event-based Neural Networks" is accepted at RA-L.
  • [07/08/2022] EvAC3D: From Event-Based Apparent Contours to 3D Models via Continuous Visual Hulls" is selected as Oral Presentation at ECCV 2022. See you in Tel Aviv!

Research

My main research interests are event-based vision, 3D computer vision and robotics. In particular, I work on motion and scene understanding of highly dynamic scenes. My research projects range from fundamental geometry problems in event-based vision to applications of the event sensors in real robots.

EqNIO: Subequivariant Neural Inertial Odometry
Royina Karegoudra Jayanth* Yinshuang Xu* Ziyun Wang, Evangelos Chatzipantazis, Daniel Gehrig, Kostas Daniilidis

Paper

Un-EVIMO: Unsupervised Event-based Independent Motion Segmentation
Ziyun Wang, Jinyuan Guo, Kostas Daniilidis
European Conference on Computer Vision (ECCV), 2024
project page / Paper

Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation
Friedhelm Hamman, Ziyun Wang, Ioannis Asmanis, Kenneth Chaney, Guillermo Gallego, Kostas Daniilidis
European Conference on Computer Vision (ECCV), 2024
project page / Paper

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos
Yufu Wang, Ziyun Wang, Lingjie Liu, Kostas Daniilidis
European Conference on Computer Vision (ECCV), 2024
project page / Paper

Track Everything Everywhere Fast and Robustly
Yunzhou Song*, JiahuiLei*, Ziyun Wang, Lingjie Liu, Kostas Daniilidis
European Conference on Computer Vision (ECCV), 2024
project page / Paper

Event-based Continuous Color Video Decompression from Single Frames
Ziyun Wang, Friedhelm Hamann, Kenneth Chaney, Wan Jiang, Guillermo Gallego, Kostas Daniilidis

project page / Paper

M3ED: Multi-Robot, Multi-Sensor, Multi-Environment Event Dataset
Kenneth Channey*, Fernando Cladera*, Ziyun Wang, Anthony Bisulco, M Ani Hsieh, Christopher Korpela, Vijay Kumar, Camillo J Taylor, Kostas Daniilidis
Event-based Vision Workshop, CVPR 2023
project page / paper

EvAC3D: From Event-Based Apparent Contours to 3D Models via Continuous Visual Hulls
Ziyun Wang*, Kenneth Channey*, Kostas Daniilidis
European Conference on Computer Vision (ECCV), 2022 (Oral Presentation, 2.7% Top Papers)
project page / Paper

EV-Catcher: High-Speed Object Catching Using Low-Latency Event-Based Neural Networks
Ziyun Wang*, Fernando Cladera*, Anthony Bisculco, Daewon Lee, Camillo J Taylor, Kostas Daniilidis, M Ani Hsieh , Daniel D Lee , Volkan Isler
IEEE Robotics and Automation Letters (RA-L), 2022
Paper

Eventgan: Leveraging large scale image datasets for event cameras
Alex Zhu, Ziyun Wang, Kaung Khant, Kostas Daniilidis,
IEEE International Conference on Computational Photography (ICCP), 2021
Paper

Learning to generate cost-to-go functions for efficient motion planning
Jinwook Huh, Galen Xing, Ziyun Wang, Volkan Isler, Daniel D. Lee
Experimental Robotics: The 17th International Symposium, 2021
Paper

Surface HOF: Surface Reconstruction from a Single Image Using Higher Order Function Networks
Ziyun Wang, Volkan Isler, Daniel D. Lee
IEEE International Conference on Image Processing (ICIP), 2020
Paper

Geodesic-HOF: 3D Reconstruction Without Cutting Corners
Ziyun Wang, Eric Mitchell, Volkan Isler, Daniel D. Lee
AAAI Conference on Artificial Intelligence, 2021
Paper

Motion Equivariant Networks for Event Cameras with the Temporal Normalization Transform
Alex Zhu, Ziyun Wang, Kostas Daniilidis

Paper

Robustness Meets Deep Learning: An End-to-End Hybrid Pipeline for Unsupervised Learning of Egomotion
Alex Zhu, Wenxin Liu, Ziyun Wang, Vijay Kumar, Kostas Daniilidis
Workshop on Deep Learning for Semantic Visual Navigation, CVPR 2019
Paper