AvatarMAV：使用运动感知神经体素的快速3D头部化身重建
AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxels
AI总结：
针对基于NeRF的3D头部化身重建训练耗时长的问题，提出AvatarMAV方法，通过与3DMM表情基对应的4D张量加权拼接生成运动感知神经体素，实现仅5分钟的快速高质量重建。
摘要：
随着NeRF（神经辐射场）被广泛用于面部重演，近期方法仅通过单目视频就能重建出照片级真实感的3D头部化身。遗憾的是，基于NeRF的方法训练过程十分耗时，因为这类方法所用的MLP（多层感知器）效率低下，需要极多次迭代才能收敛。为解决该问题，我们提出AvatarMAV——一种采用运动感知神经体素的快速3D头部化身重建方法。AvatarMAV是首个通过神经体素同时建模头部化身的规范外观与解耦表情运动的方法。具体而言，运动感知神经体素由多个4D张量加权拼接生成，这些4D张量与3DMM（三维形变模型）表情基在语义上一一对应，且权重与3DMM表情系数一致。得益于这一新型表示，我们提出的AvatarMAV仅需5分钟（纯PyTorch实现）就能重建照片级真实感头部化身，速度显著快于当前最先进的面部重演方法。项目页面：https://www.liuyebin.com/avatarmav。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
