Guoguang Du

Short Bio

News

• 2025 Jun: DropletVideo is accepted by ICCV (Highlight). Project
• 2020 Nov: I gave a talk in "智东西" on "Vision-based Robotic Grasping, [Slides].
• 2019 Oct: Paper list in GitHub: Vision-based Robotic Grasping: Papers and Codes.

Working Experience

• IEIT SYSTEMS Co., Ltd. Dec. 2022 – now
  Researcher
  Large-Scale Video and 3D Dataset Construction, Multi-Modal Video/3D Generation
• Realsee Group, KE Holdings Inc. Apr. 2021 – Dec. 2022
  Senior Algorithm Engineer
  Audio-Driven 2D/3D Face Animation
• SmartVision Group, CloudMinds Jan. 2018 – Apr. 2021
  Senior Algorithm Engineer
  Object-Related 3D Detection, 6D Pose Estimation, and Robotic Grasp Estimation
• AR Lab, Baidu Jun. 2017 – Sep. 2017
  3D Vision Intern
  Automatic Evaluation of Visual SLAM

Selected Publications

• Language-Guided Compositional 3D Scene Generation via Fine-Grained Part-level 3D Representation
  Shenhao Zhang, Yuhang Han, Menglei Yang, Guoguang Du^*.
  IPMML, 2025.
  [Paper]
• Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation
  Xiaochuan Li, Guoguang Du, Runze Zhang, Liang Jin, Qi Jia, Lihua Lu, Zhenhua Guo, Yaqian Zhao, Haiyang Liu, Tianqi Wang, Changsheng Li, Xiaoli Gong, Rengang Li, Baoyu Fan.
  arXiv, 2025.
  [Paper] [Project] [Code]
• DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation
  Runze Zhang, Guoguang Du, Xiaochuan Li, Qi Jia, Liang Jin, Lu Liu, Jingjing Wang, Cong Xu, Zhenhua Guo, Yaqian Zhao, Xiaoli Gong, Rengang Li, Baoyu Fan.
  ICCV, 2025.
  [Paper] [Project] [Code]
• Advances in Text-Guided 3D Editing: A Survey
  Lihua Lu, Ruyang Li, Xiaohui Zhang, Hui Wei, Guoguang Du, Binqiang Wang.
  Artificial Intelligence Review, 2024.
  [Paper]
• Infer Induced Sentiment of Comment Response to Video: A new Task, Dataset and Baseline
  Qi Jia, Baoyu Fan, Cong Xu, Lu Liu, Liang Jin, Guoguang Du, Zhenhua Guo, Yaqian Zhao, Xuanjing Huang, Rengang Li.
  NeurIPS, 2024.
  [Paper]
• Method for Detecting Grasping Position of Robot in Grasping Object
  Guoguang Du, Kai Wang, Shiguo Lian.
  US Patent, 2024.
  [Patent]
• Deepvio: Self-supervised Deep Learning of Monocular Visual Inertial Odometry Using 3D Geometric Constraints
  Liming Han, Yimin Lin, Guoguang Du, Shiguo Lian.
  IROS, 2019.
  [Paper]
• Deep Global-Relative Networks for End-to-end 6-dof Visual Localization and Odometry
  Yimin Lin, Zhaoxiang Liu, Jianfeng Huang, Chaopeng Wang, Guoguang Du, Jinqiang Bai, Shiguo Lian.
  Pacific Rim International Conference on Artificial Intelligence, 2019.
  [Paper]
• Vision-based Robotic Grasping From Object Localization, Object Pose Estimation To Grasp Estimation for Parallel Grippers: A Review
  Guoguang Du, Kai Wang, Shiguo Lian, Kaiyong Zhao.
  Artificial Intelligence Review, 2021.
  [Paper]
• Real-Time 3D Object Detection and Tracking in Monocular Images of Cluttered Environment
  Guoguang Du, Kai Wang, Yibing Nan, Shiguo Lian.
  International Conference on Image and Graphics, 2019.
  [Paper]
• Part-in-whole Matching of Rigid 3D Shapes Using Geodesic Disk Spectrum
  Guoguang Du, Congli Yin, Mingquan Zhou, Zhongke Wu, Fuqing Duan.
  Multimedia Tools and Applications, 2018.
  [Paper]
• Isometric 3D Shape Partial Matching Using GD-DNA
  Guoguang Du, CongLi Yin, MingQuan Zhou, ZhongKe Wu, YaChun Fan, FuQing Duan, PengBo Zhou.
  Journal of Computer Science & Technology, 2018.
  [Paper]
• Classifying Fragments of Terracotta Warriors Using Template-based Partial Matching
  Guoguang Du, Mingquan Zhou, Congli Yin, Zhongke Wu, Wuyang Shui.
  Multimedia Tools and Applications, 2018.
  [Paper]
• An Automatic Positioning Algorithm for Archaeological Fragments
  Guoguang Du, Mingquan Zhou, Congli Yin, Juan Zhang, Zhongke Wu, Wuyang Shui.
  Proceedings of the 15th ACM SIGGRAPH Conference on VRCAI, 2016.
  [Paper]