Most learning methods for 3D data (point clouds, meshes) suffer significant performance drops when the data is not carefully aligned to a canonical orientation. Aligning real world 3D data collected from different sources is non-trivial and requires manual intervention. In this paper, we propose the Adjoint Rigid Transform (ART) Network, a neural module which can be integrated with a variety of 3D networks to significantly boost their performance. ART learns to rotate input shapes to a learned canonical orientation, which is crucial for a lot of tasks such as shape reconstruction, interpolation, non-rigid registration, and latent disentanglement. ART achieves this with self-supervision and a rotation equivariance constraint on predicted rotations. The remarkable result is that with only self-supervision, ART facilitates learning a unique canonical orientation for both rigid and nonrigid shapes, which leads to a notable boost in performance of aforementioned tasks. We will release our code and pre-trained models for further research.

翻译：大多数针对三维数据（点云、网格）的学习方法在数据未仔细对齐至标准姿态时，性能会显著下降。而对来自不同来源的真实三维数据进行对齐并非易事，通常需要人工干预。本文提出伴随刚体变换网络（ART）——一种可集成到多种三维网络中的神经模块，能够显著提升其性能。ART通过学习将输入形状旋转至学习的标准姿态，这对形状重建、插值、非刚性配准及潜在空间解耦等任务至关重要。该网络通过自监督学习与旋转等变性约束实现这一目标，其显著成果在于：仅依赖自监督，ART即可为刚性和非刚性形状建立统一的标准姿态，从而显著提升上述任务的性能。我们将在后续研究中公开代码与预训练模型。