Tangent Convolutions for Dense Prediction in 3D
Abstract
We present an approach to semantic scene analysis using deep convolutional networks. Our approach is based on tangent convolutions - a new construction for convolutional networks on 3D data. In contrast to volumetric approaches, our method operates directly on surface geometry. Crucially, the construction is applicable to unstructured point clouds and other noisy real-world data. We show that tangent convolutions can be evaluated efficiently on large-scale point clouds with millions of points. Using tangent convolutions, we design a deep fully-convolutional network for semantic segmentation of 3D point clouds, and apply it to challenging real-world datasets of indoor and outdoor 3D environments. Experimental results show that the presented approach outperforms other recent deep network constructions in detailed analysis of large 3D scenes.
Cite
Text
Tatarchenko et al. "Tangent Convolutions for Dense Prediction in 3D." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00409Markdown
[Tatarchenko et al. "Tangent Convolutions for Dense Prediction in 3D." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/tatarchenko2018cvpr-tangent/) doi:10.1109/CVPR.2018.00409BibTeX
@inproceedings{tatarchenko2018cvpr-tangent,
title = {{Tangent Convolutions for Dense Prediction in 3D}},
author = {Tatarchenko, Maxim and Park, Jaesik and Koltun, Vladlen and Zhou, Qian-Yi},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2018},
doi = {10.1109/CVPR.2018.00409},
url = {https://mlanthology.org/cvpr/2018/tatarchenko2018cvpr-tangent/}
}