@article{Guo2020, 
author = {Jianwei Guo and Hanyu Wang and Zhanglin Cheng and Xiaopeng Zhang and Dong-Ming Yan},
title = {Learning local shape descriptors for computing non-rigid dense correspondence},
year = {2020},
journal = {Computational Visual Media},
volume = {6},
number = {1},
pages = {95-112},
keywords = {local feature descriptor, triplet CNN, dense correspondence, geometry image, non-rigid shape},
url = {https://www.sciopen.com/article/10.1007/s41095-020-0163-y},
doi = {10.1007/s41095-020-0163-y},
abstract = {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.}
}