# Novel Class Discovery for 3D Point Cloud Semantic Segmentation Source: [Novel Class Discovery for 3D Point Cloud Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2026-01-04T04:29:26.452Z Authors: Luigi Riz, Cristiano Saltori, Elisa Ricci, Fabio Poiesi Published: 2023-03-21T06:10:39.000Z ## Abstract Novel class discovery (NCD) for semantic segmentation is the task of learning a model that can segment unlabelled (novel) classes using only the supervision from labelled (base) classes. This problem has recently been pioneered for 2D image data, but no work exists for 3D point cloud data. In fact, the assumptions made for 2D are loosely applicable to 3D in this case. This paper is presented to advance the state of the art on point cloud data analysis in four directions. Firstly, we address the new problem of NCD for point cloud semantic segmentation. Secondly, we show that the transposition of the only existing NCD method for 2D semantic segmentation to 3D data is suboptimal. Thirdly, we present a new method for NCD based on online clustering that exploits uncertainty quantification to produce prototypes for pseudo-labelling the points of the novel classes. Lastly, we introduce a new evaluation protocol to assess the performance of NCD for point cloud semantic segmentation. We thoroughly evaluate our method on SemanticKITTI and SemanticPOSS datasets, showing that it can significantly outperform the baseline. Project page at this link: https://github.com/LuigiRiz/NOPS. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [3D Semantic Segmentation on SemanticPOSS (POSS-3^1)](): 3D Semantic Segmentation; SemanticPOSS (POSS-3^1); IoU (Bike): 29.35. - [3D Semantic Segmentation on SemanticPOSS (POSS-4^0)](): 3D Semantic Segmentation; SemanticPOSS (POSS-4^0); IoU (bike): 35.47. - [Novel Class Discovery on SemanticKITTI KITTI-5^0](): Novel Class Discovery; SemanticKITTI KITTI-5^0; IoU (bike): 5.59. - [3D Semantic Segmentation on SemanticPOSS (POSS-3^2)](): 3D Semantic Segmentation; SemanticPOSS (POSS-3^2); Bike IoU: 37.16. - [3D Semantic Segmentation on SemanticPOSS (POSS-3^3)](): 3D Semantic Segmentation; SemanticPOSS (POSS-3^3); IoU (bike): 38.55. - [Novel Class Discovery on SemanticKITTI KITTI-5](): Novel Class Discovery; SemanticKITTI KITTI-5; IoU (bike): 7.36. - [Novel Class Discovery on SemanticKITTI KITTI-5^2](): Novel Class Discovery; SemanticKITTI KITTI-5^2; IoU (bike): 6.72. - [Novel Class Discovery on SemanticKITTI KITTI-4^3](): Novel Class Discovery; SemanticKITTI KITTI-4^3; IoU (bike): 2.32. - [Novel Class Discovery on SemanticPOSS (Split 0)](): Novel Class Discovery; SemanticPOSS (Split 0); Bike Performance: 35.5. - [Novel Class Discovery on SemanticPOSS (Split 1)](): Novel Class Discovery; SemanticPOSS (Split 1); Bike Score: 29.4. - [Novel Class Discovery on SemanticKITTI (Split 4)](): Novel Class Discovery; SemanticKITTI (Split 4); Novel Class Score: 12.4. - [Novel Class Discovery on SemanticKITTI (Split 1)](): Novel Class Discovery; SemanticKITTI (Split 1); Novel Class Score: 37.1. - [Novel Class Discovery on SemanticKITTI (Split 2)](): Novel Class Discovery; SemanticKITTI (Split 2); Novel Class Score: 25.4. - [Novel Class Discovery on SemanticKITTI (Split 3)](): Novel Class Discovery; SemanticKITTI (Split 3); Novel Class Score: 16.5. - [Novel Class Discovery on SemanticPOSS Split 2](): Novel Class Discovery; SemanticPOSS Split 2; Bike Performance: 37.2. - [Novel Class Discovery on SemanticPOSS (Split 3)](): Novel Class Discovery; SemanticPOSS (Split 3); Bike Accuracy: 38.6. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()