No augmented application is possible without animated humanoid avatars. At the same time, generating human replicas from real-world monocular hand-held or robotic sensor setups is challenging due to the limited availability of views. Previous work showed the feasibility of virtual avatars but required the presence of 360 degree views of the targeted subject. To address this issue, we propose HINT, a NeRF-based algorithm able to learn a detailed and complete human model from limited viewing angles. We achieve this by introducing a symmetry prior, regularization constraints, and training cues from large human datasets. In particular, we introduce a sagittal plane symmetry prior to the appearance of the human, directly supervise the density function of the human model using explicit 3D body modeling, and leverage a co-learned human digitization network as additional supervision for the unseen angles. As a result, our method can reconstruct complete humans even from a few viewing angles, increasing performance by more than 15% PSNR compared to previous state-of-the-art algorithms.

不加强实境应用中的动画人型化身是不可能的。我们提出了一种基于HINT的算法，能够从有限的视角学习到详细和完整的人体模型，通过引入对称先验、正则化约束和大型人体数据集提供的训练线索来解决传统方法中受限于视角可用性的问题，从而使我们的方法能够重构完整的人体，即使只有少数视角，与先前最先进算法相比，性能提高了15%以上的峰值信噪比。

从有限的视点中学习完整的人类神经表征