论文标题
avatarmav：使用运动吸引神经素的快速3D头部化身重建
AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxels
论文作者
论文摘要
通过广泛用于面部重演的NERF，最近的方法可以从单眼视频中恢复照片真实的3D头像。不幸的是，基于NERF的方法的训练过程非常耗时，因为基于NERF的方法中使用的MLP效率低下，需要太多的迭代才能收敛。为了克服这个问题，我们提出了Avatarmav，这是一种使用运动感知神经体素的快速3D头制化方法。阿瓦塔玛夫（Avatarmav）是第一个模拟典型外观和神经体素化表达运动的模型的人。特别是，运动感知的神经体素是由多个4D张量的加权串联产生的。 4D张量在语义上对应于3DMM表达基础的一对一，并具有与3DMM表达系数相同的权重。拟议的Avatarmav受益于我们的新颖代表，可以在短短5分钟内恢复光真逼真的头像（用纯Pytorch实施），这比最先进的面部重演方法要快得多。项目页面：https：//www.liuyebin.com/avatarmav。
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 methods is inefficient and requires too many iterations to converge. To overcome this problem, we propose AvatarMAV, a fast 3D head avatar reconstruction method using Motion-Aware Neural Voxels. AvatarMAV is the first to model both the canonical appearance and the decoupled expression motion by neural voxels for head avatar. In particular, the motion-aware neural voxels is generated from the weighted concatenation of multiple 4D tensors. The 4D tensors semantically correspond one-to-one with 3DMM expression basis and share the same weights as 3DMM expression coefficients. Benefiting from our novel representation, the proposed AvatarMAV can recover photo-realistic head avatars in just 5 minutes (implemented with pure PyTorch), which is significantly faster than the state-of-the-art facial reenactment methods. Project page: https://www.liuyebin.com/avatarmav.
