![\"\"](\"https:\/\/mscvprojects.ri.cmu.edu\/2022team1\/wp-content\/uploads\/sites\/56\/2022\/12\/Screenshot-2022-12-16-at-3.19.18-PM-1024x192.png\")
Our method, HLPS, employs a point-based encoder-decoder network to classify points into one of K+1<\/em> classes, as is the case in open-set recognition. In other words, the network is trained to distinguish the K<\/em> known classes from other<\/em>. In the second stage, we run a non-learned clustering algorithm on both things<\/em> and other<\/em> points, and learn a scoring function to get an instance segmentation. This is illustrated in Fig 1. Each component of our proposed method is explained below in further detail.<\/p>\n\n\n\n We use the well-consolidated Kernel-Point Convolution (KPConv) [1] backbone to operate directly on an input point cloud. We attach a semantic classifier on top of the decoder feature representation to output a semantic map which consists of K+1<\/em> classes. The network is trained using cross-entropy loss.<\/p>\n\n\n\n We first group points based on their spatial proximity using hierarchical clustering (HDBSCAN), which results in a hierarchy of segments (Fig 2-mid). From this segmentation tree, there exist combinatorially many per-point instance segmentation possibilities. Therefore, to get an instance segmentation from this tree, we need to make a cut through this tree (Fig 2-right). <\/p>\n\n\n\n To generate a cut from this tree, we learn a function which estimates how likely a subset a points represent an object. We use a PointNet classification network trained with a mean-squared error loss function, with an objective to regress the IoU of the segment with its matched ground-truth instance. <\/p>\n\n\n\n Given this function, we need to find where to cut this tree such that an overall segmentation score is as good as possible. In [2], it is shown that if the global segmentation score is defined as the worst objectness in the tree, the worst-case segmentation leads to an optimal cut (which can be obtained efficiently using dynamic programming).<\/p>\n\n\n\nSemantic Segmentation<\/h3>\n\n\n\n
Object segmentation via point clustering<\/h3>\n\n\n\n
![\"\"](\"https:\/\/mscvprojects.ri.cmu.edu\/2022team1\/wp-content\/uploads\/sites\/56\/2022\/12\/Screenshot-2022-12-16-at-3.32.30-PM-1024x326.png\")
References<\/h3>\n\n\n\n