Skip to main content
Fig. 1 | IPSJ Transactions on Computer Vision and Applications

Fig. 1

From: Pseudo-labelling-aided semantic segmentation on sparsely annotated 3D point clouds

Fig. 1

Illustration of our method. Colours indicate the class of points, which are red: foliage, yellow: wire, green: pole, light blue: ground, and blue: façade. a Small number of initial annotation to point cloud is given. b Our method performs learning and propagation sequentially. c In the end, all points are labelled. See that our method does not only propagate, but also labels points without initially labelled points in its neighbourhood

Back to article page