Learning Relationships for Multi-View 3D Object Recognition

Ze Yang, Liwei Wang; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 7505-7514

Abstract


Recognizing 3D object has attracted plenty of attention recently, and view-based methods have achieved best results until now. However, previous view-based methods ignore the region-to-region and view-to-view relationships between different view images, which are crucial for multi-view 3D object representation. To tackle this problem, we propose a Relation Network to effectively connect corresponding regions from different viewpoints, and therefore reinforce the information of individual view image. In addition, the Relation Network exploits the inter-relationships over a group of views, and integrates those views to obtain a discriminative 3D object representation. Systematic experiments conducted on ModelNet dataset demonstrate the effectiveness of our proposed methods for both 3D object recognition and retrieval tasks.

Related Material


[pdf]
[bibtex]
@InProceedings{Yang_2019_ICCV,
author = {Yang, Ze and Wang, Liwei},
title = {Learning Relationships for Multi-View 3D Object Recognition},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}