Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Xu, Yuelang"'
Creating high-fidelity 3D human head avatars is crucial for applications in VR/AR, digital human, and film production. Recent advances have leveraged morphable face models to generate animated head avatars from easily accessible data, representing va
Externí odkaz:
http://arxiv.org/abs/2407.15070
Autor:
Liao, Zhanfeng, Xu, Yuelang, Li, Zhe, Li, Qijing, Zhou, Boyao, Bai, Ruifeng, Xu, Di, Zhang, Hongwen, Liu, Yebin
Creating high-fidelity 3D head avatars has always been a research hotspot, but it remains a great challenge under lightweight sparse view setups. In this paper, we propose HHAvatar represented by controllable 3D Gaussians for high-fidelity head avata
Externí odkaz:
http://arxiv.org/abs/2312.03029
One crucial aspect of 3D head avatar reconstruction lies in the details of facial expressions. Although recent NeRF-based photo-realistic 3D head avatar methods achieve high-quality avatar rendering, they still encounter challenges retaining intricat
Externí odkaz:
http://arxiv.org/abs/2310.06275
Autor:
Xu, Yuelang, Zhang, Hongwen, Wang, Lizhen, Zhao, Xiaochen, Huang, Han, Qi, Guojun, Liu, Yebin
Existing approaches to animatable NeRF-based head avatars are either built upon face templates or use the expression coefficients of templates as the driving signal. Despite the promising progress, their performances are heavily bound by the expressi
Externí odkaz:
http://arxiv.org/abs/2305.01190
With NeRF widely used for facial reenactment, recent methods can recover photo-realistic 3D head avatar from just a monocular video. Unfortunately, the training process of the NeRF-based methods is quite time-consuming, as MLP used in the NeRF-based
Externí odkaz:
http://arxiv.org/abs/2211.13206
Autor:
Wang, Xiaogang, Xu, Yuelang, Xu, Kai, Tagliasacchi, Andrea, Zhou, Bin, Mahdavi-Amiri, Ali, Zhang, Hao
We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data. We represent these edges as a collection of parametric curves (i.e.,lines, circles, and B-splines). Accordingly, our deep neural network, coined
Externí odkaz:
http://arxiv.org/abs/2007.04883