Ziyang Song
Researcher at 腾讯
Hong Kong, China
Summary
👤
Senior🎓
Top SchoolZiyang Song is a researcher and PhD candidate at The Hong Kong Polytechnic University with eight years of experience in computer vision and machine learning, currently focusing on 3D object segmentation, reconstruction, and editing. He has industry research experience at major labs including Tencent, SenseTime, and TikTok, working on video generation, world models for filmmaking, and 3D human motion synthesis (ActFormer, ICCV 2023). Comfortable bridging academic rigor and production constraints, he has implemented real-time action recognition on mobile platforms and contributed to reference-to-video generation projects. Based in Hong Kong, Ziyang combines deep technical expertise with practical system-building skills, often exploring ways to make 3D vision methods more usable in creative content pipelines.
8 years of coding experience
Doctor of Philosophy - PhD Computing, Doctor of Philosophy - PhD Computing at The Hong Kong Polytechnic UniversityMaster of Engineering - MEng Automation, Master of Engineering - MEng Automation at Xi'an Jiaotong University
Github Skills (71)
python10
image-processing10
computer-vision10
unsupervised-learning10
sdk9
object-detection9
opencv9
computer-graphics9
deep-learning9
machine-learning9
keras9
tensorflow9
point-cloud9
hyperparameter-tuning8
mask8
Programming languages (2)
Github contributions (5)
vLAR-group/OGC
Jul 2022 - Nov 2022
🔥OGC in PyTorch (NeurIPS 2022 & TPAMI 2024)
Contributions:21 commits, 1 PR, 11 pushes in 4 months
pytorchgeometric-deep-learningunsupervised-learningneuripsobject-detection
Szy-Young/Notes
May 2021 - Sep 2022
Contributions:68 commits, 68 pushes, 1 branch in 1 year 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.