Learning Relationships for Multi-View 3D Object Recognition
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.
Cite
Text
Yang and Wang. "Learning Relationships for Multi-View 3D Object Recognition." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00760Markdown
[Yang and Wang. "Learning Relationships for Multi-View 3D Object Recognition." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/yang2019iccv-learning-a/) doi:10.1109/ICCV.2019.00760BibTeX
@inproceedings{yang2019iccv-learning-a,
title = {{Learning Relationships for Multi-View 3D Object Recognition}},
author = {Yang, Ze and Wang, Liwei},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
year = {2019},
doi = {10.1109/ICCV.2019.00760},
url = {https://mlanthology.org/iccv/2019/yang2019iccv-learning-a/}
}