TY - GEN
T1 - Self-Supervised Learning of Local Features in 3D Point Clouds
AU - Thabet, Ali Kassem
AU - Alwassel, Humam
AU - Ghanem, Bernard
N1 - KAUST Repository Item: Exported on 2020-10-01
PY - 2020
Y1 - 2020
N2 - We present a self-supervised task on point clouds, in order to learn meaningful point-wise features that encode local structure around each point. Our self-supervised network, operates directly on unstructured/unordered point clouds. Using a multi-layer RNN, our architecture predicts the next point in a point sequence created by a popular and fast Space Filling Curve, the Morton-order curve. The final RNN state (coined Morton feature) is versatile and can be used in generic 3D tasks on point clouds. Our experiments show how our self-supervised task results in features that are useful for 3D segmentation tasks, and generalize well between datasets. We show how Morton features can be used to significantly improve performance (+3% for 2 popular algorithms) in semantic segmentation of point clouds on the challenging and large-scale S3DIS dataset. We also show how our self-supervised network pretrained on S3DIS transfers well to another large-scale dataset, vKITTI, leading to 11% improvement. Our code is publicly available.1
AB - We present a self-supervised task on point clouds, in order to learn meaningful point-wise features that encode local structure around each point. Our self-supervised network, operates directly on unstructured/unordered point clouds. Using a multi-layer RNN, our architecture predicts the next point in a point sequence created by a popular and fast Space Filling Curve, the Morton-order curve. The final RNN state (coined Morton feature) is versatile and can be used in generic 3D tasks on point clouds. Our experiments show how our self-supervised task results in features that are useful for 3D segmentation tasks, and generalize well between datasets. We show how Morton features can be used to significantly improve performance (+3% for 2 popular algorithms) in semantic segmentation of point clouds on the challenging and large-scale S3DIS dataset. We also show how our self-supervised network pretrained on S3DIS transfers well to another large-scale dataset, vKITTI, leading to 11% improvement. Our code is publicly available.1
UR - http://hdl.handle.net/10754/664502
UR - https://ieeexplore.ieee.org/document/9150706/
U2 - 10.1109/CVPRW50498.2020.00477
DO - 10.1109/CVPRW50498.2020.00477
M3 - Conference contribution
SN - 978-1-7281-9361-8
BT - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
PB - IEEE
ER -