Guocheng Qian is currently working towards an MS/Ph.D. degree in the Department of Computer Science at King Abdullah University of Science and Technology (KAUST). He is part of the Image and Video Understanding Lab (IVUL), supervised by Prof. Bernard Ghanem. During his Ph.D. studies, he interned at several leading institutions including Snap Research, Meta Reality Lab, and MEGVII research. His primary research interest lies in 3D vision.

Education and Early Career

Guocheng obtained his bachelor's degree in Engineering with first-class honors from Xi’an Jiaotong University (XJTU) in China in 2018.  He was an exchange student at the Hong Kong University of Science and Technology in early 2017 and a visiting scholar at Wakayama University in Japan in Dec 2017. Before joining KAUST, he worked at SenseTime Research in China.

Research Interest 

  • Point Cloud Understanding
  • 3D generation
  • Efficient Neural Network

Education Profile

  • B.S., Engineering, Xi'an Jiaotong University, China, 2018

Awards and Distinctions

  • CEMSE Dean’s List Award (year 21/22)
  • CEMSE Research Excellence Award (year 21/22)
  • Outstanding Undergraduate (selected to 10 undergraduates), 2017
  • National First Class Scholarship (top 2%), 2017


Lirbrary Bldg, Level 3, 3120-WS13

Selected Publications

Qian, Guocheng, Abdulellah Abualshour, Guohao Li, Ali Thabet, and Bernard Ghanem. "Pu-gcn: Point cloud upsampling using graph convolutional networks." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'21), pp. 11683-11692. 2021.
Qian, Guocheng, Hasan Hammoud, Guohao Li, Ali Thabet, and Bernard Ghanem. "Assanet: An anisotropic separable set abstraction for efficient point cloud representation learning." Advances in Neural Information Processing Systems 34 (2021): 28119-28130.
Qian, Guocheng, Yuchen Li, Houwen Peng, Jinjie Mai, Hasan Hammoud, Mohamed Elhoseiny, and Bernard Ghanem. "Pointnext: Revisiting pointnet++ with improved training and scaling strategies." Advances in Neural Information Processing Systems 35 (2022): 23192-23204.