TY - GEN
T1 - Deep Parametric Continuous Convolutional Neural Networks
AU - Wang, Shenlong
AU - Suo, Simon
AU - Ma, Wei Chiu
AU - Pokrovsky, Andrei
AU - Urtasun, Raquel
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/14
Y1 - 2018/12/14
N2 - Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes.
AB - Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes.
UR - http://www.scopus.com/inward/record.url?scp=85056797765&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85056797765&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2018.00274
DO - 10.1109/CVPR.2018.00274
M3 - Conference contribution
AN - SCOPUS:85056797765
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2589
EP - 2597
BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PB - IEEE Computer Society
T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Y2 - 18 June 2018 through 22 June 2018
ER -