3D human mesh recovery from point clouds is essential for various tasks, including AR/VR and human behavior understanding. Previous works in this field either require high-quality 3D human scans or sequential point clouds, which cannot be easily applied to low-quality 3D scans captured by consumer-level depth sensors. In this paper, we make the first attempt to reconstruct reliable 3D human shapes from single-frame partial point clouds.To achieve this, we propose an end-to-end learnable method, named VoteHMR. The core of VoteHMR is a novel occlusion-aware voting network that can first reliably produce visible joint-level features from the input partial point clouds, and then complete the joint-level features through the kinematic tree of the human skeleton. Compared with holistic features used by previous works, the joint-level features can not only effectively encode the human geometry information but also be robust to noisy inputs with self-occlusions and missing areas. By exploiting the rich complementary clues from the joint-level features and global features from the input point clouds, the proposed method encourages reliable and disentangled parameter predictions for statistical 3D human models, such as SMPL. The proposed method achieves state-of-the-art performances on two large-scale datasets, namely SURREAL and DFAUST. Furthermore, VoteHMR also demonstrates superior generalization ability on real-world datasets, such as Berkeley MHAD.
翻译:从点云中恢复3D人类网格对于各种任务至关重要,包括AR/VR和人类行为理解。该领域以前的工作要么需要高质量的3D人扫描,要么需要连续的点云,这不能轻易地应用于消费级深度传感器所捕捉的低质量3D扫描。在本文件中,我们第一次尝试从单一框架部分点云中重建可靠的3D人形。为了实现这一点,我们提议了一个端到端的学习方法,名为“VoiceHMR”。 投票HMR的核心是一个全新的隐蔽-觉投票网络,它首先能够可靠地从输入点云部分云中产生可见的联合级别特征,然后通过人类骨骼的运动树完成联合级别特征。与以往工作使用的整体特征相比,联合级别不仅能够有效地将人类的测深信息编码起来,而且能够用自我封闭和缺失的区域来扰动输入。通过利用来自联合层次特征和输入点云的全球特征的丰富互补线索,拟议的方法鼓励可靠和混乱的更高水平能力通过人类骨质的骨质骨质树来完成统计3LA级的数据模型,即SMA-deal-deal-deal-deal-deal-deal-deal laxal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal salvial sal sal sal sal sal sal sal salvial sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal