基于自适应多类中心和半异构网络的三维模型草图检索

草图具有易于构建且不受语言、专业、年龄限制等优势,基于手绘草图的三维模型检索受到越来越多的关注.然而在三维模型草图检索任务中,三维模型具有复杂性,草图具有类内多样性,同时三维模型与草图之间又具有巨大的域间差异性,这些特点的相互作用严重影响检索的准确性.针对以上问题,提出了一种基于自适应多类中心和半异构网络的三维模型草图...

Adaptive multi-class centers and semi-heterogeneous network for sketch-based 3D model retrieval

Sketches are advantageous in being easy to construct and unrestricted by language, discipline, age, and soforth, and the 3D model retrieval based on hand-drawn sketches has attracted increasing attention. However, due tothe complexity of 3D models, intra-class diversity of 2D sketches, and the inter-domain differences between 3Dmodels and 2D sketches, the sketch-based 3D model retrieval remains highly challenging currently. To address theseissues, we proposed a 3D model retrieval for sketch based on adaptive multi-class centers and semi-heterogeneousnetwork. First, the initial features of the sketches and the 3D models were extracted separately through twoheterogeneous networks: a sketch feature embedding sub-network based on adaptive multi-class centers was designedto capture the intra-class diversity of sketches, and a 3D model feature embedding sub-network based on multi-view feature fusion was adopted to adapt to the complexity of 3D models. Then, using the label vectors with rich semanticinformation as guides, a homogeneous network was designed to realize the cross-domain shared feature embedding ofthe sketches and 3D models, so as to reduce the inter-domain differences. Comparative experiments on the largepublic data sets SHREC2013 and SHREC2014 demonstrate that the proposed algorithm is on par with or better thanthe state-of-the-art methods.