Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds

TL;DR

This paper introduces the first generative zero-shot learning approach for semantic segmentation of 3D point clouds, outperforming existing methods on multiple benchmarks and establishing new evaluation standards.

Contribution

It presents a novel generative ZSL and GZSL method for 3D data that handles both classification and semantic segmentation, a first in the field.

Findings

Outperforms state-of-the-art on ModelNet40 classification

Creates three new benchmarks for 3D ZSL segmentation

Outperforms strong baseline methods on these benchmarks

Abstract

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.