About me

I am a Research Scientist at the Intelligent Creation Lab, ByteDance/TikTok. I completed my Ph.D. in VCC, KAUST, supervised by Prof. Peter Wonka. Before that, I obtained the M.Sc. degree from KAUST, KSA, and the B.Eng. degree from Northeastern University, China. My research is mainly related to representation learning and generative models. I am also interested in computer graphics and computer vision in general.

You can find my full CV here.

Publications

2022

3DAvatarGAN: Bridging Domains for Personalized Editable Avatars
Rameen Abdal, Hsin-Ying Lee, Peihao Zhu, Menglei Chai, Aliaksandr Siarohin , Peter Wonka,Sergey Tulyakov
Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
paper

HairNet: Hairstyle Transfer with Pose Changes
Peihao Zhu, Rameen Abdal, John Femiani, Peter Wonka
Proc. European Conference on Computer Vision (ECCV), 2022
video

CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directions
Rameen Abdal ,Peihao Zhu,John Femiani, Niloy J. Mitra,Peter Wonka
SIGGRAPH Conference Proceedings, 2022
paper 

Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks
Peihao Zhu, Rameen Abdal, John Femiani, Peter Wonka
International Conference on Learning Representations (ICLR), 2022
paper  code  video

2021

Barbershop: GAN-based Image Compositing using Segmentation Masks
Peihao Zhu, Rameen Abdal, John Femiani, Peter Wonka
ACM Transactions on Graphics (Proc. SIGGRAPH Asia), 2021
paper  code  video

Improved StyleGAN Embedding: Where are the Good Latents?
Peihao Zhu, Rameen Abdal, Yipeng Qin, John Femiani, Peter Wonka
ArXiv pre-print, 2021
paper   video

Styleflow: Attribute-conditioned exploration of stylegan-generated images using conditional continuous normalizing flows
Rameen Abdal, Peihao Zhu, Niloy J. Mitra, Peter Wonka
ACM Transactions on Graphics (TOG), 2021
paper   code  video

Labels4Free: Unsupervised Segmentation using StyleGAN
Rameen Abdal, Peihao Zhu, Niloy J. Mitra, Peter Wonka
Proc. IEEE International Conference on Computer Vision (ICCV), 2021
paper code   video

Flow-Guided Video Inpainting with Scene Templates
Dong Lao, Peihao Zhu, Peter Wonka, Ganesh Sundaramoorthi
Proc. IEEE International Conference on Computer Vision (ICCV), 2021
paper

2020

SEAN: Image Synthesis with Semantic Region-Adaptive Normalization
Peihao Zhu, Rameen Abdal, Yipeng Qin, Peter Wonka
Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR Oral), 2020
paper  code  video

Large Scale Architecture Asset Extraction from Panoramic Imagery
Peihao Zhu, Wamiq Reyaz Para, Anna Fruehstueck, John Femiani, Peter Wonka
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2020
paper  code  video

Education

Ph.D. in Computer Science
KAUST, Visual Computing Center
2019 - 2023

M.Sc. in Computer Science
KAUST, Visual Computing Center
2017 - 2019

B.Eng. in Automation
Northeastern University
2012 - 2016


Research Experience

Creative Vision, Snap Research Research Intern

May 2022 - Sep 2022


Reality Lab, Meta                       Research Intern

Oct 2022 - Feb 2023


Contact

Address
KAUST, Thuwal, Saudi Arabia

Email
peihao.zhu@kaust.edu.sa

Phone
(+1) 4242939085