GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians
Harbin Institute of Technology · Beijing Normal University · +1 more institution
Abstract
We present GaussianAvatar, an efficient approach to cre-ating realistic human avatars with dynamic 3D appear-ances from a single video. We start by introducing animat-able 3D Gaussians to explicitly represent humans in var-ious poses and clothing styles. Such an explicit and ani-matable representation can fuse 3D appearances more effi-ciently and consistently from 2D observations. Our repre-sentation is further augmented with dynamic properties to support pose-dependent appearance modeling, where a dy-namic appearance network along with an optimizable feature tensor is designed to learn the motion-to-appearance mapping. Moreover, by leveraging the differentiable motion condition, our method enables a joint…
Citation impact
- FWCI
- 45.18
- Percentile
- 100%
- References
- 79
Authors
7Topics & keywords
- Avatar
- Computer science
- Computer graphics (images)
- Human–computer interaction
- Computer vision
- Solid modeling
- Artificial intelligence