摘要
A discriminative local shape descriptor plays an important role in various applications.In this paper,we present a novel deep learning framework that derives discriminative local descriptors for deformable 3D shapes.We use local"geometry images"to encode the multi-scale local features of a point,via an intrinsic parameterization method based on geodesic polar coordinates.This new parameterization provides robust geometry images even for badly-shaped triangular meshes.Then a triplet network with shared architecture and parameters is used to perform deep metric learning;its aim is to distinguish between similar and dissimilar pairs of points.Additionally,a newly designed triplet loss function is minimized for improved,accurate training of the triplet network.To solve the dense correspondence problem,an efficient sampling approach is utilized to achieve a good compromise between training performance and descriptor quality.During testing,given a geometry image of a point of interest,our network outputs a discriminative local descriptor for it.Extensive testing of non-rigid dense shape matching on a variety of benchmarks demonstrates the superiority of the proposed descriptors over the state-of-the-art alternatives.
A discriminative local shape descriptor plays an important role in various applications. In this paper, we present a novel deep learning framework that derives discriminative local descriptors for deformable 3D shapes. We use local "geometry images" to encode the multi-scale local features of a point, via an intrinsic parameterization method based on geodesic polar coordinates. This new parameterization provides robust geometry images even for badly-shaped triangular meshes. Then a triplet network with shared architecture and parameters is used to perform deep metric learning;its aim is to distinguish between similar and dissimilar pairs of points. Additionally, a newly designed triplet loss function is minimized for improved, accurate training of the triplet network. To solve the dense correspondence problem, an efficient sampling approach is utilized to achieve a good compromise between training performance and descriptor quality. During testing,given a geometry image of a point of interest, our network outputs a discriminative local descriptor for it.Extensive testing of non-rigid dense shape matching on a variety of benchmarks demonstrates the superiority of the proposed descriptors over the state-of-the-art alternatives.
基金
partially funded by the National Key R&D Program of China(2018YFB2100602)
the National Natural Science Foundation of China(61802406,61772523,61702488)
Beijing Natural Science Foundation(L182059)
the CCF–Tencent Open Research Fund,Shenzhen Basic Research Program(JCYJ20180507182222355)
the Open Project Program of the State Key Lab of CAD&CG(A2004)Zhejiang University.
