Chao Xu

Ph.D. Candidate (Year 3)

Email

chaoxu@ucla.edu

Short Bio

I am currently a third-year Ph.D. student at the Center for Vision, Cognition, Learning, and Autonomy (VCLA), University of California, Los Angeles (UCLA), advised by Prof. Song-Chun Zhu. I received dual bachelor degrees in Computer Engineering from University of Illinois at Urbana-Champaign and Zhejiang University.

My research interests are focused on the fields of computer vision, robotics, and cognitive science. I actively engaged in pushing the boundaries of generalizable object understanding and enhancing 3D vision through visual-language models.

[CV]

News

  • Feb. 2023 - GAPartNet accepted to CVPR 2023 Highlight (10% of accepted, scores: 5, 5, 5).
  • Sep. 2022 - Our awesome course Cognitive Reasoning is available. I designed the affordance learning section (slide available upon request).
  • June 2022 - Advanced to candidacy.
  • Dec. 2021 - Invited talk at MURI Annual Meeting.
  • May 2021 - Research intern at Beijing Institute for General Artificial Intelligence (BIGAI).
  • Sept. 2020 - Start Ph.D. research at VCLA@UCLA.

Publications

GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts
Haoran Geng*, Helin Xu*, Chengyang Zhao*, Chao Xu, Li Yi, Siyuan Huang, He Wang
CVPR 2023 Highlight (10% of accepted, scores: 5, 5, 5)
[Paper] [Project]
We propose to learn cross-category object perception and manipulation skills via Generalizable and Actionable Parts (GAParts). By identifying 9 GAPart classes (lids, handles, etc.) in 27 object categories, we construct GAPartNet, where we provide rich, part-level annotations (semantics, poses) for 8,489 part instances on 1,166 objects.

PartAfford: Part‑level Affordance Discovery from Cross‑category 3D Objects
Chao Xu, Yixin Chen, He Wang, Song-Chun Zhu, Yixin Zhu, Siyuan Huang
ECCV 2022 Visual Object-oriented Learning meets Interaction Workshop
[Paper] [Video]
We present a new task of part-level affordance discovery (PartAfford): Given only the affordance labels per object, the machine is tasked to (i) decompose 3D shapes into parts and (ii) discover how each part of the object corresponds to a certain affordance category.

Education

University of Illinois at Urbana-Champaign
B.S. Computer Engineering | 2016 - 2020
GPA: 3.90/4.00

Zhejiang University
B.Eng. Electronics and Computer Engineering | 2016 - 2020
GPA: 3.92/4.00