Semantic-Preserved Point-based Human Avatar
This work addresses the need for efficient and intuitive human avatar animation in applications like virtual try-on, though it appears incremental as it builds on existing models like SMPL-X.
The paper tackles the problem of creating realistic human avatars for AR/VR and digital entertainment by introducing a point-based model that preserves semantic information, resulting in reduced training and inference times compared to implicit methods.
To enable realistic experience in AR/VR and digital entertainment, we present the first point-based human avatar model that embodies the entirety expressive range of digital humans. We employ two MLPs to model pose-dependent deformation and linear skinning (LBS) weights. The representation of appearance relies on a decoder and the features that attached to each point. In contrast to alternative implicit approaches, the oriented points representation not only provides a more intuitive way to model human avatar animation but also significantly reduces both training and inference time. Moreover, we propose a novel method to transfer semantic information from the SMPL-X model to the points, which enables to better understand human body movements. By leveraging the semantic information of points, we can facilitate virtual try-on and human avatar composition through exchanging the points of same category across different subjects. Experimental results demonstrate the efficacy of our presented method.