Type
ArticleKAUST Department
Computer Science ProgramComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Visual Computing Center (VCC)
Date
2020-08-12Preprint Posting Date
2020-01-28Online Publication Date
2020-08-12Print Publication Date
2020-07-08Permanent link to this record
http://hdl.handle.net/10754/661684
Metadata
Show full item recordAbstract
We propose a novel framework for computing descriptors for characterizing points on three-dimensional surfaces. First, we present a new non-learned feature that uses graph wavelets to decompose the Dirichlet energy on a surface. We call this new feature Wavelet Energy Decomposition Signature (WEDS). Second, we propose a new Multiscale Graph Convolutional Network (MGCN) to transform a non-learned feature to a more discriminative descriptor. Our results show that the new descriptor WEDS is more discriminative than the current state-of-the-art non-learned descriptors and that the combination of WEDS and MGCN is better than the state-of-the-art learned descriptors. An important design criterion for our descriptor is the robustness to different surface discretizations including triangulations with varying numbers of vertices. Our results demonstrate that previous graph convolutional networks significantly overfit to a particular resolution or even a particular triangulation, but MGCN generalizes well to different surface discretizations. In addition, MGCN is compatible with previous descriptors and it can also be used to improve the performance of other descriptors, such as the heat kernel signature, the wave kernel signature, or the local point signature.Citation
Wang, Y., Ren, J., Yan, D.-M., Guo, J., Zhang, X., & Wonka, P. (2020). MGCN. ACM Transactions on Graphics, 39(4). doi:10.1145/3386569.3392443Journal
ACM Transactions on GraphicsarXiv
2001.10472Additional Links
https://dl.acm.org/doi/10.1145/3386569.3392443ae974a485f413a2113503eed53cd6c53
10.1145/3386569.3392443