Xiangyu Zhu

Xiangyu Zhu

Associate Professor

Short Bio

I am now an Associate Professor at Institute of Automation Chinese Academic of Sciences (CASIA). My research interest includes machine learning and pattern recognition, especially 3D face reconstruction, face recognition, and Explainable AI. I am awarded the “Young Biometrics Investigator Award (YBIA)” by the International Association of Pattern Recognition (IAPR) in 2023 (awarded biennially to one scholar under 40 worldwide). I won the Champion of the Face Recognition Challenges at WACV 2024 and ICCV 2017, CCBR Best Student Paper Award (2017), Best Poster Paper Award (2022), and Best Paper 1st Runner Up (2023). I have published more 80 papers with total citation in Google Scholar being 8700. I am an IEEE senior member and serve as the area chair for IJCB and ACM MM.

中国科学院自动化研究所副研究员，从事生物特征识别和可解释AI相关基础理论研究与应用。国际模式识别协会（IAPR）生物特征青年学者奖（YBIA）获得者（两年一次，每次从全球范围内评选40岁以下学者一名），中国图象图形学学会青托俱乐部副主席。共发表论文80余篇，其中作为第一作者发表T-PAMI论文 3篇，IJCV论文1篇，两次获得CVPR口头报告，发表文章的Google Scholar总引用次数为8700余次。获得三次国际竞赛冠军以及四项最佳论文及提名奖。授权国家发明专利10项。入选IEEE Senior Member，百度学术全球华人AI青年学者榜单（全球25人），受到腾讯犀牛鸟基金支持。获2021中国电子学会科技进步二等奖、中国图象图形学学会优秀博士论文提名奖，提出的人脸三维建模方法在被PyTorch官方Twitter报道，单篇论文（一作）引用次数1200余次，开源代码在Github上收获6000余星。


News!

  • Apr. 2024: One paper on 6DoF Face Pose Estimation is accepted by IEEE Transactions on Multimedia (TMM).
  • Mar. 2024: Our 3DDFAv3 Paper “3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation” is accepted by CVPR 2024 (Highlight).
  • Mar. 2024: We won the WACV 2024 Face Recognition Challenge in the Era of Synthetic Data (FRCSyn). Congrats to all collaborators!
  • Dec. 2023: We won the Best Paper 1st Runner Up in CCBR 2023. Congrats to YangTe!
  • Oct. 2023: I am awarded the IAPR Young Biometrics Investigator Award (YBIA). Thanks IAPR TC4 committee [Link].
  • Mar. 2023: My paper (first author) is accepted by TBIOM, and one paper is accepted by TIP.
  • Mar. 2023: Four papers are accepted by CVPR. Congrats to all collaborators!
  • Feb. 2023: We won the Best Poster Paper in CCBR 2022. Congrats to Tianshuo!
  • Feb. 2023: My paper (first author) is accepted by T-PAMI.
  • May. 2022: I am selected by Baidu Xueshu 2022 Global Top Chinese Young Scholars in AI. （百度学术2022年全球华人AI青年学者榜单）
  • Apr. 2022: I am supported by Tencent AI Lab Rhino-Bird Focused Research Program. （腾讯AI Lab犀牛鸟专项研究计划）
  • Apr. 2022: My paper (first author) is accepted by T-PAMI.
  • Mar. 2022: One paper working on Capsule Network accepted by CVPR 2022.
  • Jan. 2022: One paper accepted by ICLR 2022.
  • Jan. 2022: Obtain Second Class Prize of the Science and Technology Award, Chinese Institute of Electronics. （中国电子学会科学技术二等奖）


Education

  • Ph.D in Institute of Automation, Chinese Academic of Sciences, 2017, supervised by Prof. Stan Z. Li
  • B.S. in College of Computer Science, Sichuan University, 2012


Work experience

  • 2019～now: Associate Professor
    • National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
  • 2017～2019: Assistant Professor
    • National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences


Selected Publications

 

3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation,
Zidu Wang, Xiangyu Zhu (corresponding author), Tianshuo Zhang, Baiqin Wang and Zhen Lei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Highlight 2024.
[PDF][3DDFAv3 Github]

 

Face Forgery Detection by 3D Decomposition and Composition Search,
Xiangyu Zhu, Hongyan Fei, Bin Zhang, Tianshuo Zhang, Xiaoyu Zhang, Stan Z. Li, Zhen Lei
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023.
[PDF]

 

Graphics Capsule: Learning Hierarchical 3D Face Representations from 2D Images,
Chang Yu, Xiangyu Zhu (corresponding author), Xiaomei Zhang, Zhaoxiang Zhang, Zhen Lei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[PDF]

 

MVP-Human Dataset for 3D Clothed Human Avatar Reconstruction from Multiple Frames,
Xiangyu Zhu, Tingting Liao, Xiaomei Zhang, Jiangjing Lyu, Zhiwen Chen, Yunfeng Wang, Kan Guo, Qiong Cao, Stan Z. Li, Zhen Lei
IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM), 2023.
[PDF][Github]

 

Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape,
Xiangyu Zhu, Chang Yu, Di Huang, Zhen Lei, Hao Wang, Stan Z. Li
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2022.
[PDF]

 

HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network,
Chang Yu, Xiangyu Zhu, Xiaomei Zhang, Zidu Wang, Zhaoxiang Zhang, Zhen Lei
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[PDF]

 

Face Forgery Detection by 3D Decomposition,
Xiangyu Zhu, Hao Wang, Hongyan Fei, Zhen Lei, Stan Z. Li.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Oral, 2021.
[PDF]

 

Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction,
Xiangyu Zhu, Fan Yang, Di Huang, Chang Yu, Hao Wang, Jianzhu Guo, Zhen Lei, Stan Z. Li.
In European Conference on Computer Vision (ECCV), 2020.
[PDF][Github]

 

Towards Fast, Accurate and Stable 3D Dense Face Alignment,
Jianzhu Guo, Xiangyu Zhu, Yang Yang, Fan Yang, Zhen Lei, Stan Z. Li. (co-first author).
In European Conference on Computer Vision (ECCV), 2020.
[PDF] [Github]

 

Large-scale Bisample Learning on ID versus Spot Face Recognition,
Xiangyu Zhu, Hao Liu, Zhen Lei, Hailin Shi, Fan Yang, Dong Yi, Guojun Qi, Stan Z. Li.
Special issue on Deep Learning for Face Analysis. International Journal of Computer Vision (IJCV)，2019.
[PDF][Project]

 

Face Alignment In Full Pose Range: A 3D Total Solution,
Xiangyu Zhu, Xiaoming Liu, Zhen Lei, Stan Z. Li.
IEEE transactions on pattern analysis and machine intelligence (T-PAMI), 2017, 41(1): 78-92.
[PDF][Supplemental Material][Github]

 

Face Alignment Across Large Poses: A 3D Solution,
Xiangyu Zhu, Zhen Lei, Xiaoming Liu, Hailin Shi, Stan Z. Li.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Oral, 2016.
[PDF][Supplemental Material][Github][300W-LP][AFLW2000-3D]

 

High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild,
Xiangyu Zhu, Zhen Lei, Junjie Yan, Dong Yi, Stan Z. Li.
In Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR).Boston, June 7-12, 2015.
[PDF][Supplemental Material][Project]


Honors & Awards

  • IAPR Young Biometrics Investigator Award 2023 (YBIA) (Honors a scholar under the age of 40 who has made substantial contributions to the IAPR Biometrics community and whose research has had a major impact in biometrics.) [Link]
  • IEEE Senior Member
  • CSIG Senior Member
  • 2023 CCBR Best Paper 1st Runner Up.
  • 2022 CCBR Best Poster Paper Award.
  • 2022 Baidu Xueshu 2022 Global Top Chinese Young Scholars in AI. （百度学术2022年全球华人AI青年学者榜单）
  • 2022 Tencent AI Lab Rhino-Bird Focused Research Program. （腾讯AI Lab犀牛鸟专项研究计划）
  • 2021 Second Class Prize of the Science and Technology Award, Chinese Institute of Electronics. （中国电子学会科学技术二等奖）
  • 2021 Young Elite Scientist Sponsorship Program by Beijing Association for Science and Technology. （北京科协青年人才托举工程）
  • 2020 Member of the Youth Innovation Promotion Association, Chinese Academy of Sciences. （中国科学院青年创新促进会）
  • 2019 Best Doctoral Dissertation Finalist, China Society of Image and Graphics (CSIG).
  • 2018 ICME Best Student Paper Award Runner-up.
  • 2017 CCBR Best Student Paper Award.

Competitions