Abstract | ||
---|---|---|
Labelling point clouds fully is highly time-consuming and costly. As larger point cloud datasets with billions of points become more common, we ask whether the full annotation is even necessary, demonstrating that existing baselines designed under a fully annotated assumption only degrade slightly even when faced with 1% random point annotations. However, beyond this point, e.g., at 0.1% annotations, segmentation accuracy is unacceptably low. We observe that, as point clouds are samples of the 3D world, the distribution of points in a local neighbourhood is relatively homogeneous, exhibiting strong semantic similarity. Motivated by this, we propose a new weak supervision method to implicitly augment highly sparse supervision signals. Extensive experiments demonstrate the proposed Semantic Query Network (SQN) achieves promising performance on seven large-scale open datasets under weak supervision schemes, while requiring only 0.1% randomly annotated points for training, greatly reducing annotation cost and effort. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1007/978-3-031-19812-0_35 | European Conference on Computer Vision |
Keywords | DocType | Citations |
Semantic query,Weak supervision,Large-scale point clouds | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qingyong Hu | 1 | 51 | 9.25 |
B. Yang | 2 | 69 | 7.63 |
Guangchi Fang | 3 | 0 | 0.68 |
Yulan Guo | 4 | 672 | 50.74 |
Ales Leonardis | 5 | 1636 | 147.33 |
Niki Trigoni | 6 | 1160 | 85.23 |
Andrew Markham | 7 | 519 | 48.34 |