Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels
This reduces labeling costs for 3D point cloud segmentation, which is incremental as it builds on existing supervised methods.
The paper tackles the problem of costly 3D point cloud segmentation labels by proposing a weakly supervised approach that uses only a tiny fraction of labeled points, achieving results close to or better than fully supervised methods with 10 times fewer labels.
Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. The success of existing approaches is attributed to deep network design and large amount of labelled training data, where the latter is assumed to be always available. However, obtaining 3d point cloud segmentation labels is often very costly in practice. In this work, we propose a weakly supervised point cloud segmentation approach which requires only a tiny fraction of points to be labelled in the training stage. This is made possible by learning gradient approximation and exploitation of additional spatial and color smoothness constraints. Experiments are done on three public datasets with different degrees of weak supervision. In particular, our proposed method can produce results that are close to and sometimes even better than its fully supervised counterpart with 10$\times$ fewer labels.