TY - GEN
T1 - Point Cloud Instance Segmentation using Probabilistic Embeddings
AU - Zhang, Biao
AU - Wonka, Peter
N1 - KAUST Repository Item: Exported on 2021-11-05
PY - 2021
Y1 - 2021
N2 - In this paper we propose a new framework for point cloud instance segmentation. Our framework has two steps: an embedding step and a clustering step. In the embedding step, our main contribution is to propose a probabilistic embedding space for point cloud embedding. Specifically, each point is represented as a tri-variate normal distribution. In the clustering step, we propose a novel loss function, which benefits both the semantic segmentation and the clustering. Our experimental results show important improvements to the SOTA, i.e., 3.1% increased average per-category mAP on the PartNet dataset.
AB - In this paper we propose a new framework for point cloud instance segmentation. Our framework has two steps: an embedding step and a clustering step. In the embedding step, our main contribution is to propose a probabilistic embedding space for point cloud embedding. Specifically, each point is represented as a tri-variate normal distribution. In the clustering step, we propose a novel loss function, which benefits both the semantic segmentation and the clustering. Our experimental results show important improvements to the SOTA, i.e., 3.1% increased average per-category mAP on the PartNet dataset.
UR - http://hdl.handle.net/10754/660736
UR - https://ieeexplore.ieee.org/document/9578383/
U2 - 10.1109/CVPR46437.2021.00877
DO - 10.1109/CVPR46437.2021.00877
M3 - Conference contribution
SN - 978-1-6654-4510-8
BT - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PB - IEEE
ER -