Domain-aware Category-level Geometry Learning Segmentation for 3D Point Clouds

TL;DR

This paper introduces a novel framework for 3D point cloud segmentation that leverages category-level geometric features to improve domain generalization, outperforming existing methods.

Contribution

It proposes Category-level Geometry Embedding and Geometric Consistent Learning to capture domain-invariant geometric features for better generalization.

Findings

Achieves competitive segmentation accuracy on unseen domains.

Effectively aligns category-level geometric embeddings across domains.

Outperforms state-of-the-art domain generalization methods.

Abstract

Domain generalization in 3D segmentation is a critical challenge in deploying models to unseen environments. Current methods mitigate the domain shift by augmenting the data distribution of point clouds. However, the model learns global geometric patterns in point clouds while ignoring the category-level distribution and alignment. In this paper, a category-level geometry learning framework is proposed to explore the domain-invariant geometric features for domain generalized 3D semantic segmentation. Specifically, Category-level Geometry Embedding (CGE) is proposed to perceive the fine-grained geometric properties of point cloud features, which constructs the geometric properties of each class and couples geometric embedding to semantic learning. Secondly, Geometric Consistent Learning (GCL) is proposed to simulate the latent 3D distribution and align the category-level geometric embeddings, allowing the model to focus on the geometric invariant information to improve generalization. Experimental results verify the effectiveness of the proposed method, which has very competitive segmentation accuracy compared with the state-of-the-art domain generalized point cloud methods.