Fig. 2From: Pseudo-labelling-aided semantic segmentation on sparsely annotated 3D point cloudsSemantic segmentation results. From the left to right, the results for the Oakland, Semantic3D, and S3DIS (with RGB) datasets are shown. a The ground truth, b predictions made using Seg-aided [17], c predictions made by our supervised baseline, d prediction results made by our method without kdist or krgb, e predictions made by our methods with kdist (for the Oakland and Semantic3D datasets) or with kdist and krgb (for S3DIS dataset). Colours correspond to semantic classes. White dots indicate initially annotated pointsBack to article page