Learning Spectral Transform Network on 3D Surface for Non-Rigid Shape Analysis
Abstract
Designing a network on 3D surface for non-rigid shape analysis is a challenging task. In this work, we propose a novel spectral transform network on 3D surface to learn shape descriptors. The proposed network architecture consists of four stages: raw descriptor extraction, surface second-order pooling, mixture of power function-based spectral transform, and metric learning. The proposed network is simple and shallow. Quantitative experiments on challenging benchmarks show its effectiveness for non-rigid shape retrieval and classification, e.g., it achieved the highest accuracies on SHREC’14, 15 datasets as well as the “range” subset of SHREC’17 dataset.
Cite
Text
Yu et al. "Learning Spectral Transform Network on 3D Surface for Non-Rigid Shape Analysis." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11015-4_28Markdown
[Yu et al. "Learning Spectral Transform Network on 3D Surface for Non-Rigid Shape Analysis." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/yu2018eccvw-learning/) doi:10.1007/978-3-030-11015-4_28BibTeX
@inproceedings{yu2018eccvw-learning,
title = {{Learning Spectral Transform Network on 3D Surface for Non-Rigid Shape Analysis}},
author = {Yu, Ruixuan and Sun, Jian and Li, Huibin},
booktitle = {European Conference on Computer Vision Workshops},
year = {2018},
pages = {377-394},
doi = {10.1007/978-3-030-11015-4_28},
url = {https://mlanthology.org/eccvw/2018/yu2018eccvw-learning/}
}