Learning Spectral Transform Network on 3D Surface for Non-rigid Shape Analysis

Ruixuan Yu, Jian Sun, Huibin Li; The European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Yu_2018_ECCV_Workshops,
author = {Yu, Ruixuan and Sun, Jian and Li, Huibin},
title = {Learning Spectral Transform Network on 3D Surface for Non-rigid Shape Analysis},
booktitle = {The European Conference on Computer Vision (ECCV) Workshops},
month = {September},
year = {2018}
}