Ziyan Wang

Email:
wzygundam13[AT]
gmail[DOT]com
github google scholar [CV]

About Me

Hi! I am currenly a research scientist at Reality Labs Research Sausalito. I have obtained my PhD from the Robitics institute at Carnegie Mellon University, where I was very fortunate to be advised by Jessica Hodgins. During my PhD study, I worked as a visiting research at Reality Labs Research (Codec Avatar) for two years where I was lucky to have collaborated with many brilliant folks like Christoph Lassner, Michael Zollhoefer, Stephen Lombardi, Giljoo Nam, Tuur Stuyck, Jason Saragih and so many others. My research interests lie in computer vision and machine learning, with a focus on 3D/4D representation, neural rendering and generative models.

I earned my master's degree in Dec. 2018 from the Robotics Institue at Carnegie Mellon University where I worked with Prof. Katerina Fragkiadaki and Prof. Simon Lucey. Prior to CMU, I received my bachelar's degree from the Department of Automation at Tsinghua University in China, advised by Prof. Jiwen Lu. In summer 2018, I have the fortunate to work with Dr. Samuel Schulter, Dr. Buyu Liu and Prof. Manmohan Chandraker in Media Analytics Group at NEC Labs, America. In 2016, I spent my summer in Vision & Learning Lab at the University of Michigan, Ann Arbor as a research assistant, supervised by Prof. Jia Deng.

Publications

A Local Appearance Model for Volumetric Capture of Diverse Hairstyles
Ziyan Wang, Giljoo Nam, Aljaz Bozic, Chen Cao, Jason Saragih, Michael Zollhöfer, Jessica Hodgins,
To appear in the International Conference on 3D Vision (3DV) 2024
[paper] [project page]

CT2Hair: High-Fidelity 3D Hair Modeling using Computed Tomography
Yuefan Shen, Shunsuke Saito, Ziyan Wang, Olivier Maury, Chenglei Wu, Jessica Hodgins, Youyi Zheng, Giljoo Nam,
ACM SIGGRAPH 2023 (ACM Transactions on Graphics), Selected in the Technical Papers Video Trailer
[paper] [project page] [video] [code]

NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation
Ziyan Wang, Giljoo Nam, Tuur Stuyck, Stephen Lombardi, Chen Cao, Jason Saragih, Michael Zollhöfer, Jessica Hodgins, Christoph Lassner
IEEE Conference on Computer Vision and Pattern Recognition(CVPR) 2023
[paper] [arxiv] [project page] [bibtex]

Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images
Radu Alexandru Rosu, Shunsuke Saito, Ziyan Wang, Chenglei Wu, Sven Behnke, Giljoo Nam
European Conference on Computer Vision (ECCV) 2022
[paper] [arxiv] [project page] [bibtex]

HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capture
Ziyan Wang, Giljoo Nam, Tuur Stuyck, Stephen Lombardi, Michael Zollhöfer Jessica Hodgins, Christoph Lassner
IEEE Conference on Computer Vision and Pattern Recognition(CVPR) 2022
[paper] [arxiv] [project page] [bibtex]

Learning Compositional Radiance Fields of Dynamic Human Heads
Ziyan Wang, Timur Bagautdinov, Stephen Lombardi, Tomas Simon, Jason Saragih, Jessica Hodgins, Michael Zollhöfer
IEEE Conference on Computer Vision and Pattern Recognition(CVPR) 2021, Oral (top 4.19%)
[paper] [arxiv] [project page] [bibtex]

A Parametric Top-View Representation of Complex Road Scenes
Ziyan Wang, Buyu Liu, Samuel Schulter, Manmohan Chandraker
IEEE Conference on Computer Vision and Pattern Recognition(CVPR) 2019
[paper] [supp] [arxiv] [project page] [bibtex]

Geometry-Aware Recurrent Neural Networks for Active Visual Recognition
Ricson Cheng*, Ziyan Wang*, Katerina Fragkiadaki
Advances in Neural Information Processing Systems(NIPS) 2018
[paper] [arxiv] [code] [bibtex]

Semantic Photometric Bundle Adjustment on Natural Sequences
Rui Zhu, Chaoyang Wang, Ziyan Wang, Chen-Hsuan Lin, Simon Lucey
Arxiv, IEEE Winter Conference on Applications of Computer Vision(WACV) 2018
[arxiv] [paper] [demo]

Virtual to Real Reinforcement Learning for Autonomous Driving
Xinlei Pan*, Yurong You*, Ziyan Wang, Cewu Lu
British Machine Vision Conference(BMVC) 2017, spotlight
[arxiv] [code] [video]

Correlated and Individual Multi-Modal Deep Learning for RGB-D Object Recognition
Ziyan Wang, Jiwen Lu, Ruogu Lin, Jiangjiang Feng, Jie Zhou
Arxiv
[arxiv]

Education

Carnegie Mellon University, US
Ph.D. in Robotics, Aug. 2019 - Sept. 2023
M.S. in Computer Vision, Aug. 2017 - Dec. 2018
Tsinghua University, China
B.Eng in Automation, Aug. 2013 - Jun. 2017