1 code implementation • 4 Dec 2023 • Liangxiao Hu, Hongwen Zhang, Yuxiang Zhang, Boyao Zhou, Boning Liu, Shengping Zhang, Liqiang Nie
We present GaussianAvatar, an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video.
1 code implementation • 4 Dec 2023 • Shunyuan Zheng, Boyao Zhou, Ruizhi Shao, Boning Liu, Shengping Zhang, Liqiang Nie, Yebin Liu
We present a new approach, termed GPS-Gaussian, for synthesizing novel views of a character in a real-time manner.
no code implementations • 8 May 2023 • Zerong Zheng, Xiaochen Zhao, Hongwen Zhang, Boning Liu, Yebin Liu
We present AvatarReX, a new method for learning NeRF-based full-body avatars from video data.
no code implementations • CVPR 2023 • Ruizhi Shao, Zerong Zheng, Hanzhang Tu, Boning Liu, Hongwen Zhang, Yebin Liu
The key of our solution is an efficient 4D tensor decomposition method so that the dynamic scene can be directly represented as a 4D spatio-temporal tensor.
1 code implementation • 21 Nov 2022 • Ruizhi Shao, Zerong Zheng, Hanzhang Tu, Boning Liu, Hongwen Zhang, Yebin Liu
The key of our solution is an efficient 4D tensor decomposition method so that the dynamic scene can be directly represented as a 4D spatio-temporal tensor.
no code implementations • 14 Aug 2021 • Boning Liu, Yan Zhao, Xiaomeng Jiang, Shigang Wang, Jian Wei
A 4-D Epanechnikov mixture regression (4-D EMR) was proposed based on this 4-D EK, and a 4-D adaptive model selection (4-D AMLS) algorithm was designed to realize the optimal modeling for a pseudo video sequence (PVS) of the extracted key-EIA.
no code implementations • 3 Jun 2021 • Boning Liu, Yan Zhao, Xiaomeng Jiang, Shigang Wang
We propose a three-dimensional (3-D) Epanechnikov Mixture Regression (EMR) based on our Epanechnikov Kernel (EK) and realize a complete framework for image coding.