Kerui Gu

About Me

I am a fourth-year Ph.D. student at Department of Computer Science, National University of Singapore (NUS), supervised by Prof. Angela Yao. My research interests lie in computer vision and deep learning, especially human pose estimation. I achieved my Bachelor’s degree at Shanghai Jiao Tong University (SJTU). Previsouly, I worked with Prof. Quanshi Zhang@SJTU and Prof. Guosheng Lin@NTU.

News

• 03/24: A paper on Pose Calibration is accepted to ICML2024!
• 03/24: A paper on Mesh Recovery is accepted to CVPR2024, Congrats to Fengyuan!
• 11/23: Two co-authored papers accepted to Neurips2023 and WACV2024, Congrats to Pengzhan and Qiuxia!
• 07/23: Attended ICVSS2023 in beautiful Sicily!
• 03/23: One first author paper accepted to TPAMI!
• 03/23: One paper accepted to CVPR2023!
• 01/22: One first author paper accepted to ICLR2022!
• 01/22: Received Research Achievement Award from SoC@NUS!
• 12/21: Passed Qualification Exam!
• 07/21: One first author paper accepted to ICCV2021!

Preprints

• Learning Unorthogonalized Matrices for Rotation Estimation
  Kerui Gu, Zhihao Li, Jianzhuang Liu, Songcen Xu, Youliang Yan, Michael Bi Mi, Kenji Kawaguchi, Angela Yao
  [paper]
• OfCam: Global Human Mesh Recovery via Optimization-free Camera Motion Scale
  Fengyuan Yang, Kerui Gu, Linh Nguyen, Angela Yao
  [paper]

Publications

• On the Calibration of Human Pose Estimation
  Kerui Gu*, Rongyu Chen*, Xuanlong Yu, Angela Yao
  International Conference on Machine Learning. ICML 2024.
  [project page] [paper]
• KITRO: Refining Human Mesh by 2D Clues and Kinematic-tree Rotation
  Fengyuan Yang, Kerui Gu, Angela Yao
  The IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR2024.
  [project page]
• Synthetic-to-Real Pose Estimation with Geometric Reconstruction
  Qiuxia Lin, Kerui Gu, Linlin Yang, Angela Yao
  Neural Information Processing Systems. Neurips 2023.
  [paper]
• Rethinking Visibility in Human Pose Estimation: Occluded Pose Reasoning via Transformers
  Pengzhan Sun, Kerui Gu, Yunsong Wang, Linlin Yang, Angela Yao
  The IEEE/CVF Winter Conference on Applications of Computer Vision. WACV2024.
  [paper]
• Bias-Compensated Integral Regression for Human Pose Estimation
  Kerui Gu, Linlin Yang, Michael Bi Mi, Angela Yao
  Transaction on Pattern Analysis and Machine Intelligence. TPAMI 2023.
  [paper]
• Analyzing and Diagnosing Pose Estimation with Attributions
  Qiyuan He, Linlin Yang, Kerui Gu, Qiuxia Lin, Angela Yao
  The IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR2023.
  [paper]
  
• Dive Deeper Into Integral Pose Regression
  Kerui Gu, Linlin Yang, Angela Yao
  International Conference on Learning Representations. ICLR 2022.
  [paper]
• Removing the Bias of Integral Pose Regression
  Kerui Gu, Linlin Yang, Angela Yao
  International Conference on Computer Vision. ICCV 2021.
  [paper] [supp] [project]

Teaching

• CS4243 Computer Vision and Pattern Recognition AY21/22 Sem1, Teaching Assistant
• CS4243 Computer Vision and Pattern Recognition AY20/21 Sem1, Teaching Assistant

Powered by Jekyll and Minimal Light theme.