GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians

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.

Motion Estimation

CaPhy: Capturing Physical Properties for Animatable Human Avatars

no code implementations • ICCV 2023 • Zhaoqi Su, Liangxiao Hu, Siyou Lin, Hongwen Zhang, Shengping Zhang, Justus Thies, Yebin Liu

In contrast to previous work on 3D avatar reconstruction, our method is able to generalize to novel poses with realistic dynamic cloth deformations.

ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning

no code implementations • 3 Jul 2023 • Yuxiang Zhang, Hongwen Zhang, Liangxiao Hu, Jiajun Zhang, Hongwei Yi, Shengping Zhang, Yebin Liu

For more accurate and physically plausible predictions in world space, our network is designed to learn human motions from a human-centric perspective, which enables the understanding of the same motion captured with different camera trajectories.

3D Human Pose Estimation