Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds
This addresses the scarcity of zero-shot learning methods for 3D data, enabling semantic segmentation for unseen classes, though it is incremental by extending existing 2D techniques to 3D.
The paper tackles the problem of zero-shot learning for semantic segmentation of 3D point clouds, presenting the first generative approach that reaches or outperforms state-of-the-art on ModelNet40 classification and outperforms baselines on new segmentation benchmarks.
While there has been a number of studies on Zero-Shot Learning (ZSL) for 2D images, its application to 3D data is still recent and scarce, with just a few methods limited to classification. We present the first generative approach for both ZSL and Generalized ZSL (GZSL) on 3D data, that can handle both classification and, for the first time, semantic segmentation. We show that it reaches or outperforms the state of the art on ModelNet40 classification for both inductive ZSL and inductive GZSL. For semantic segmentation, we created three benchmarks for evaluating this new ZSL task, using S3DIS, ScanNet and SemanticKITTI. Our experiments show that our method outperforms strong baselines, which we additionally propose for this task.