Effective 3D shape retrieval and recognition are challenging but important tasks in computer vision research field, which have attracted much attention in recent decades. Although recent progress has shown significant improvement of deep learning methods on 3D shape retrieval and recognition performance, it is still under investigated of how to jointly learn an optimal representation of 3D shapes considering their relationships. To tackle this issue, we propose a multi-scale representation learning method on hypergraph for 3D shape retrieval and recognition, called multi-scale hypergraph neural network (MHGNN). In this method, the correlation among 3D shapes is formulated in a hypergraph and a hypergraph convolution process is conducted to learn the representations. Here, multiple representations can be obtained through different convolution layers, leading to multi-scale representations of 3D shapes. A fusion module is then introduced to combine these representations for 3D shape retrieval and recognition. The main advantages of our method lie in 1) the high-order correlation among 3D shapes can be investigated in the framework and 2) the joint multi-scale representation can be more robust for comparison. Comparisons with state-of-the-art methods on the public ModelNet40 dataset demonstrate remarkable performance improvement of our proposed method on the 3D shape retrieval task. Meanwhile, experiments on recognition tasks also show better results of our proposed method, which indicate the superiority of our method on learning better representation for retrieval and recognition.

中文翻译：

---

用于 3D 形状检索和识别的超图多尺度表示学习


有效的3D形状检索和识别是计算机视觉研究领域具有挑战性但重要的任务，近几十年来备受关注。尽管最近的进展表明深度学习方法在 3D 形状检索和识别性能方面取得了显着改进，但如何考虑其关系来共同学习 3D 形状的最佳表示仍在研究中。为了解决这个问题，我们提出了一种用于 3D 形状检索和识别的超图多尺度表示学习方法，称为多尺度超图神经网络（MHGNN）。在该方法中，3D 形状之间的相关性在超图中表述，并进行超图卷积过程来学习表示。在这里，可以通过不同的卷积层获得多种表示，从而产生 3D 形状的多尺度表示。然后引入融合模块来组合这些表示以进行 3D 形状检索和识别。我们的方法的主要优点在于：1）可以在框架中研究3D形状之间的高阶相关性；2）联合多尺度表示可以更鲁棒地进行比较。与公共 ModelNet40 数据集上最先进的方法的比较表明，我们提出的方法在 3D 形状检索任务上具有显着的性能改进。同时，识别任务的实验也显示了我们提出的方法的更好结果，这表明我们的方法在学习更好的检索和识别表示方面的优越性。