Runyu Ding Ph.D. student Department of Electrical and Electronic Engineering The University of Hong Kong Email: dingry977 [at] gmail [dot] com [Google Scholar]   [GitHub]

Biography

I am currently a Ph.D. student (2020-) at EEE, The University of Hong Kong, advised by Dr. Xiaojuan Qi. Before that I obtained my B.Eng. degree in the School of Software Engineering at Tsinghua University in 2020.

My research interests focus on 3D vision with deep learning, especially 3D representation learning and 3D scene understanding.

Publications

*: Equal Contribution

• RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding
  Jihan Yang*, Runyu Ding*, Zhe Wang, Xiaojuan Qi
  arXiv preprint, 2023 [Project Page]  

• PLA: Language-Driven Open-Vocabulary 3D Scene Understanding
  Runyu Ding*, Jihan Yang*, Chuhui Xue, Wenqing Zhang, Song Bai, Xiaojuan Qi
  Computer Vision and Pattern Recognition Conference (CVPR), 2023 [Project Page] [Code]  

• Towards Efficient 3D Object Detection with Knowledge Distillation
  Jihan Yang, Shaoshuai Shi, Runyu Ding, Zhe Wang, Xiaojuan Qi
  Advances in Neural Information Processing Systems (NeurIPS) 2022. [Code]  

• DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation
  Runyu Ding*, Jihan Yang*, Xiaojuan Qi
  European Conference on Computer Vision (ECCV), 2022. [Code]

• PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
  Mutian Xu*, Runyu Ding*, Hengshuang Zhao, Xiaojuan Qi
  Computer Vision and Pattern Recognition Conference (CVPR), 2021. [Code]

Experiences

• Research Intern, ByteDance.
  March 2022 - Present
  
  Working with Dr. Song Bai.

• Research Intern, SenseTime Research.
  Oct. 2020 - Aug. 2021
  
  Working with Prof. Jifeng Dai.

• Research Intern, STCA Microsoft.

  July 2019 - Aug. 2019
  
  

Activities

Conference Reviewer: CVPR, ICCV, ECCV

Invited Talk:

• Language-Driven Open-Vocabulary 3D Scene Understanding. C3DV Workshop in CVPR 2023.
  

• Language-Driven Open-Vocabulary 3D Scene Understanding. VALSE 2023.
  

• DODA: Data-Oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation. Zhidongxi.
  

• PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds. Jiangmen.
  

Education

• The University of Hong Kong
  Sept. 2020 - Present
  
  Ph.D. Student at CVMI-Lab
  

• Tsinghua University
  Sept. 2015 - June 2020
  
  Bachelor Degree in Software Engineering
  GPA 3.91/4.0. Ranking 3/84.

Honors & Awards

Hong Kong PhD Fellowship Award (HKPFS)	2020
Good Graduate of Tsinghua University	2020
Outstanding Graduate of School of Software, Tsinghua University	2020

---