Foundation Model assisted Weakly Supervised LiDAR Semantic Segmentation

arXiv:2404.12861v1 Announce Type: new
Abstract: Current point cloud semantic segmentation has achieved great advances when given sufficient labels. However, the dense annotation of LiDAR point clouds remains prohibitively expensive and time-consuming, unable to keep up with the continuously growing volume of data. In this paper, we propose annotating images with scattered points, followed by utilizing SAM (a Foundation model) to generate semantic segmentation labels for the images. Finally, by mapping the segmentation labels of the images to the LiDAR space …

abstract advances annotation arxiv cloud cs.cv current data foundation foundation model however images labels lidar paper segmentation semantic type