2D image-based 3D model retrieval has become a hotspot topic in recent years. However, the current existing methods are limited by two aspects. Firstly, they are mostly based on the supervised learning, which limits their application because of the high time and cost consuming of manual annotation. Secondly, the mainstream methods narrow the discrepancy between 2D and 3D domains mainly by the image-level alignment, which may bring the additional noise during the image transformation and influence cross-domain effect. Consequently, we propose a Wasserstein distance feature alignment learning (WDFAL) for this retrieval task. First of all, we describe 3D models through a series of virtual views and use CNNs to extract features. Secondly, we design a domain critic network based on the Wasserstein distance to narrow the discrepancy between two domains. Compared to the image-level alignment, we reduce the domain gap by the feature-level distribution alignment to avoid introducing additional noise. Finally, we extract the visual features from 2D and 3D domains, and calculate their similarity by utilizing Euclidean distance. The extensive experiments can validate the superiority of the WDFAL method.

基于2D图像的3D模型检索成为近年来的热点话题。然而，目前现有的方法受到两个方面的限制。首先，它们大多基于监督学习，由于人工标注的时间和成本很高，这限制了它们的应用。其次，主流方法主要通过图像级对齐来缩小2D和3D域之间的差异，这可能会在图像转换过程中带来额外的噪声并影响跨域效果。因此，我们为该检索任务提出了 Wasserstein 距离特征对齐学习（WDFAL）。首先，我们通过一系列虚拟视图来描述 3D 模型，并使用 CNN 来提取特征。其次，我们设计了一个基于 Wasserstein 距离的域评论网络来缩小两个域之间的差异。与图像级对齐相比，我们通过特征级分布对齐来减少域间隙，以避免引入额外的噪声。最后，我们从 2D 和 3D 域中提取视觉特征，并利用欧几里德距离计算它们的相似度。大量的实验可以验证 WDFAL 方法的优越性。