伴随刚体变换网络：三维形状的任务条件对齐
Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes
AI总结：
本文提出伴随刚体变换网络（ART），通过自监督和旋转等变性约束学习将三维形状对齐到规范方向，可集成到多种三维网络中，显著提升形状重建、插值、非刚体配准和潜在解耦等任务的性能。
摘要：
大多数针对三维数据（点云、网格）的学习方法在数据未被仔细对齐到规范方向时会出现显著的性能下降。对来自不同来源的真实世界三维数据进行对齐并非易事，并且需要人工干预。在本文中，我们提出了伴随刚体变换（Adjoint Rigid Transform, ART）网络，这是一个神经模块，可以与多种三维网络集成，从而显著提升其性能。ART 学习将输入形状旋转到学习到的规范方向，这对于形状重建、插值、非刚体配准以及潜在解耦等许多任务至关重要。ART 通过自监督和对预测旋转施加旋转等变性约束来实现这一目标。显著的结果是，仅依靠自监督，ART 就有助于为刚体和非刚体形状学习唯一的规范方向，从而使上述任务的性能得到显著提升。我们将发布代码和预训练模型以供进一步研究。
英文摘要：
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.
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。
