Jianzhu Guo(郭建珠)

I graduated from Southeast University with B.S. in GIS (Geographical Information System). Now, I am a Ph.D. student at National Laboratory of Pattern Recognition, Chinese Academy of Sciences, supervised by Prof. Zhen Lei and Prof. Stan Z. Li, where I mainly research on face-related fields, including face recognition, 3D face, face anti-spoofing, face analysis and meta learning, deep learning.

Email:   jianzhu.guo@nlpr.ia.ac.cn   or   guojianzhu1994@foxmail.com

GitHub  /  CV  /  CV_EN  /  Google Scholar  /  WeChat  /  LinkedIn  /  Blog

Looking for a full-time job.

profile photo

Publications

project image

Towards Fast, Accurate and Stable 3D Dense Face Alignment


Jianzhu Guo, Xiangyu Zhu, Yang Yang, Zhen Lei, Yang Fan, Stan Z. Li
ECCV 2020
paper / supp / video / code /

We propose a novel regression framework which makes a balance among speed, accuracy and stability. Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously. To further improve the stability on videos, we present a virtual synthesis method to transform one still image to a short-video incorporating in-plane and out-of-plane face moving. Our model runs at over 50fps on a single CPU core and outperforms other state-of-the-art heavy models simultaneously. Code and models will be available at https://github.com/cleardusk/3DDFA_V2.

project image

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
ECCV 2020
code /

We propose a solution to construct large-scale fi ne-grained 3D data from RGB-D images, and construct a new dataset Fine-Grained 3D face (FG3D) with 200k samples for training. We also propose a Fine-Grained reconstruction Network (FGNet) concentrating on shape modi cation by warping the network input and output to the UV space. The proposed method and code will be available at https://github.com/XiangyuZhu-open/Beyond3DMM.

project image

Learning Meta Face Recognition in Unseen Domains


Jianzhu Guo, Xiangyu Zhu, Chenxu Zhao, Dong Cao, Zhen Lei, Stan Z. Li
CVPR 2020 (Oral Presentation, acceptance rate 5%)
arxiv / paper / code /

We propose a novel face recognition method via meta-learning named Meta Face Recognition (MFR) to learn a generalized model performing well on unseen domains. Besides, we propose two benchmarks for generalized face recognition evaluation. The proposed benchmarks will be available at https://github.com/cleardusk/MFR.

project image

Domain Balancing: Face Recognition on Long-Tailed Domains


Dong Cao, Xiangyu Zhu, Xingyu Huang, Jianzhu Guo, Zhen Lei
CVPR 2020
arxiv / paper /

This paper proposes a Domain Frequency Instructor (DFI), a light weighted Residual Balancing Mapping (RBM) block and a Domain Balancing Margin (DBM) to improve generalization on tailed domains.

project image

Improving Face Anti-Spoofing by 3D Virtual Synthesis


Jianzhu Guo, Xiangyu Zhu, Jinchuan Xiao, Zhen Lei, Genxun Wan, Stan Z. Li
International Conference On Biometrics, ICB 2019 (Oral Presentation, acceptance rate 11.2%)
arxiv / paper /

We present a method to synthesize virtual spoof data in 3D space to improve face anti-spoofing. The synthetic virtual samples can significantly boost the anti-spoofing performance when combined with a proposed data balancing strategy.

project image

Face Synthesis for Eyeglass-Robust Face Recognition


Jianzhu Guo, Xiangyu Zhu, Zhen Lei, Stan Z. Li
CCF Chinese Conference on Biometric Recognition (CCBR2018), Urumqi, China, Aug. 11-12, 2018
arxiv / paper / code /

In the application of face recognition, eyeglasses could significantly degrade the recognition accuracy. In this paper, we propose to address this problem in a virtual synthesis manner.

project image

Dominant and Complementary Emotion Recognition From Still Images of Faces


Jianzhu Guo, Zhen Lei, Jun Wan, et al.
IEEE Access, 6(1), 26391-26403, 2018
paper / code /

External journal version.

project image

Multi-modality Network with Visual and Geometrical Information for Micro Emotion Recognition


Jianzhu Guo, Shuai Zhou, Jinlin Wu, Jun Wan, Xiangyu Zhu, Zhen Lei, Stan Z. Li
FG2017, Washington, DC. May 30 –June 3, 2017
paper / code /

Winner of face micro-emotion competition held on FG 2017.

project image

3DMA: A Multi-modality 3D Mask Face Anti-spoofing Database


Jinchuan Xiao, Yinhang Tang, Jianzhu Guo, Yang Yang, Xiangyu Zhu, Zhen Lei, Stan Z. Li
16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2019
paper /

We release a multi-modality 3D mask face anti-spoofing database named 3DMA, which contains 920 videos of 67 genuine subjects wearing 48 kinds of 3D masks, captured in visual (VIS) and near-infrared (NIR) modalities.




Under Review

project image

Searching for Alignment in Face Recognition


Xiaqing Xu, Qiang Meng, Jianzhu Guo, Yunxiao Qin, Chenxu Zhao
Under Review (MM-20), 2020




Competitions

  • 1-st Winner of Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head, in conjunction with FG 2017, First author. [Code]

  • HUAWEI Code Craft 2017: Awarded Silver Medal (rank 5th) in Beijing Site. Team with three members, equal contribution.



Projects (Public)

project image

3DDFA: Real-time 3D face reconstruction   [Star history]
GitHub stars GitHub forks Hits Closed Issues Open Issues

project image

MeGlass: An eyeglass face dataset collected and cleaned for face recognition evaluation
GitHub stars GitHub forks

project image

Learning Meta Face Recognition in Unseen Domains
GitHub stars GitHub forks

project image

ImageToAscii: Python tools for Image Ascii Art
GitHub stars

project image

Source code for 1st winner of face micro-emotion competition held on FG 2017.
GitHub stars

project image

UCAS utils to ease your campus life!
GitHub stars




Contact (WeChat QR Code)

profile photo





Wow, this guy's website is awesome