In recent years, multi-view learning has emerged as a promising approach for 3D shape recognition, which identifies a 3D shape based on its 2D views taken from different viewpoints. Usually, the correspondences inside a view or across different views encode the spatial arrangement of object parts and the symmetry of the object, which provide useful geometric cues for recognition. However, such view correspondences have not been explicitly and fully exploited in existing work. In this paper, we propose a correspondence-aware representation (CAR) module, which explicitly finds potential intra-view correspondences and cross-view correspondences via kk NN search in semantic space and then aggregates the shape features from the correspondences via learned transforms. Particularly, the spatial relations of correspondences in terms of their viewpoint positions and intra-view locations are taken into account for learning correspondence-aware features. Incorporating the CAR module into a ResNet-18 backbone, we propose an effective deep model called CAR-Net for 3D shape classification and retrieval. Extensive experiments have demonstrated the effectiveness of the CAR module as well as the excellent performance of the CAR-Net.

中文翻译：

---

通过对应感知深度学习进行多视图 3D 形状识别


近年来，多视图学习已成为 3D 形状识别的一种有前途的方法，它根据从不同角度获取的 2D 视图来识别 3D 形状。通常，视图内部或不同视图之间的对应关系对对象部分的空间排列和对象的对称性进行编码，这为识别提供了有用的几何线索。然而，这种视图对应关系在现有工作中尚未得到明确和充分的利用。在本文中，我们提出了一种对应感知表示（CAR）模块，该模块通过语义空间中的 kk NN 搜索明确地找到潜在的视图内对应和跨视图对应，然后通过学习的变换聚合来自对应的形状特征。特别是，为了学习对应感知特征，考虑了对应在视点位置和视图内位置方面的空间关系。将 CAR 模块合并到 ResNet-18 主干中，我们提出了一种称为 CAR-Net 的有效深度模型，用于 3D 形状分类和检索。大量的实验证明了 CAR 模块的有效性以及 CAR-Net 的优异性能。