PG_Net details

About

Short Name PG_Net
Long Name PG_Net
Website
Description This work presents a general deep learning framework for large-scale point clouds processing without voxelizations, called PGNet, which achieves accurate recognition of point clouds with real-time processing. We design noise removal methods as preprocessing which enhances the performance of subsequent tasks including classification and segmentation. We propose a novel point clouds down-sampling strategy combining inverse density sampling and gumbel softmax sampling, which strikes a great balance between efficiency and performance for large-scale point clouds processing. Through elaborate design combining feature level correlation mining and deformable convolutions based geometric aware modeling, the local feature relationships and geometric patterns can be captured. The attention mechanism is also adopted to enhance the global non-local long-range feature correlations. Finally, the feature pyramid based residual learning network architecture is designed to combine patterns at different resolutions in a memory-efficient way. The effectiveness of our method has been validated extensively on various large-scale and real-scene indoor and outdoor datasets. It turns out that it gives better performance in point clouds classification and segmentation compared with state-of-the-art methods while guaranteeing real-time performance. We have also done weakly supervised transfer learning to demonstrate the generalization capacity of our methods. Some visualizations of the inner activation of network modules are presented to interpret what has been learned by our framework.
Reference Anonymous submission
Hardware GTX 2060
Used additional training data 0
Last submission 2020-10-19 11:27:38
Is opensource 0
Number of submissions 1

Result

A_IoU OA [s] IoU 1 IoU 2 IoU 3 IoU 4 IoU 5 IoU 6 IoU 7 IoU 8
Result0.7730.94723.000.9560.9120.8810.5530.9550.4680.6610.799
Rank1181821134499179

Full Confusion Matrix

L1' L2' L3' L4' L5' L6' L7' L8'
L11414362762261013679199756180280698096
L24175221010219125771371042341303713072333
L332244600292668759967360350950
L41446731345354035419214831123371133745564862
L5337181810200588509305251932375921003612343
L615287414669719293577227213627932078115634
L797328553117514836319187775217
L8139000100128415143858332712199