Boyao Zhou

About

I am currently working as a post-doc researcher with Yebin Liu in Tsinghua University for digital humans.

In 2022, I obtained a PhD degree from INRIA Rhône-Alpes & Université Grenoble Alpes (France) under the supervision of Edmond Boyer and Jean-Sébastien Franco for the research of 3D vision. During my PhD, I was working closely with HoloLens team of Microsoft Zürich & Cambridge.

In 2018, I received an Engineer degree from Ecole Polytechnique (France) and a Master's degreee from Paris-Saclay University (France) in Data Sciences. Prior to that, I graduated from Tongji University (China).

contact: bzhou22_at_mail.tsinghua.edu.cn

Publications

	GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis Shunyuan Zheng, Boyao Zhou, Ruizhi Shao, Boning Liu, Shengping Zhang, Liqiang Nie, and Yebin Liu Computer Vision and Pattern Recognition (CVPR2024) / Project page / Code We propose GPS-Gaussian, a generalizable pixel-wise 3D Gaussian representation for synthesizing novel views of any unseen characters instantly without any fine-tuning or optimization.
	Control4D: Efficient 4D Portrait Editing with Text Ruizhi Shao, Jingxiang Sun, Cheng Peng, Zerong Zheng, Boyao Zhou, Hongwen Zhang, and Yebin Liu Computer Vision and Pattern Recognition (CVPR2024) / Project page We introduce Control4D, an innovative framework for editing dynamic 4D portraits using text instructions.
	GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians Liangxiao Hu, Hongwen Zhang, Yuxiang Zhang, Boyao Zhou, Boning Liu, Shengping Zhang, and Liqiang Nie Computer Vision and Pattern Recognition (CVPR2024) / Project page / Code We present GaussianAvatar, an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video.
	Leveraging Intrinsic Properties for Non-Rigid Garment Alignment Siyou Lin, Boyao Zhou, Zerong Zheng, Hongwen Zhang, and Yebin Liu International Conference on Computer Vision (ICCV2023) / Project page / Code We leverage intrinsic manifold properties and neural deformation fields with a coarse-to-fine two-stage method for non-rigid garment alignment.
	PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling Zhe Li, Zerong Zheng, Yuxiao Liu, Boyao Zhou, and Yebin Liu SIGGRAPH2023 Conference Proceedings / Project page / Code We propose a neural avatar representation with optimal pose embeddings for learning the dynamic human appearance.
	Human Body Shape Completion with Implicit Shape and Flow Learning Boyao Zhou, Di Meng, Jean-Sébastien Franco, and Edmond Boyer Computer Vision and Pattern Recognition (CVPR2023) We jointly learn human shape and flow with implicit representation for completing human shapes from partial observation.
	Pyramidal Signed Distance Learning for Spatio-Temporal Human Shape Completion Boyao Zhou, Jean-Sébastien Franco, Martin Delagorce, and Edmond Boyer Asian Conference on Computer Vision (ACCV2022) /Code We propose to complete human shapes in a coarse-to-fine manner from both spatial and temporal directions.
	Spatio-Temporal Human Shape Completion With Implicit Function Networks Boyao Zhou, Jean-Sébastien Franco, Federica Bogo, and Edmond Boyer International Conference on 3D Vision (3DV2021) We propose to learn a continuous implicit representation of human shapes from a sequence of partial observations.
	Reconstructing Human Body Mesh from Point Clouds by Adversarial GP Network Boyao Zhou, Jean-Sébastien Franco, Federica Bogo, Bugra Tekin, and Edmond Boyer Asian Conference on Computer Vision (ACCV2020) We propose to reconstruct template-aligned human shapes with adversarial Gaussian Process Network from sparse point clouds.