Better Call SAL: Towards Learning to Segment Anything in Lidar

arXiv:2403.13129v1 Announce Type: new
Abstract: We propose $\texttt{SAL}$ ($\texttt{S}$egment $\texttt{A}$nything in $\texttt{L}$idar) method consisting of a text-promptable zero-shot model for segmenting and classifying any object in Lidar, and a pseudo-labeling engine that facilitates model training without manual supervision. While the established paradigm for $\textit{Lidar Panoptic Segmentation}$ (LPS) relies on manual supervision for a handful of object classes defined a priori, we utilize 2D vision foundation models to generate 3D supervision "for free". Our pseudo-labels consist of instance masks and corresponding …

abstract arxiv call cs.cv cs.ro labeling lidar object panoptic segmentation paradigm segment segment anything segmentation supervision text training type zero-shot