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

2025-08-15

AI Summary

In 3D point cloud domain-generalized semantic segmentation, existing methods often neglect category-level geometric distributions and struggle to learn domain-invariant features. To address this, we propose the Category-level Geometric Learning (CGL) framework. CGL explicitly models the geometric distribution of each semantic class in the latent space via Category-level Geometric Embedding (CGE), and enforces cross-domain geometric structure alignment for the same categories through Geometric Consistency Learning (GCL). Furthermore, it jointly optimizes semantic understanding and point cloud distribution modeling to achieve semantic-geometric co-optimization. Evaluated on multiple cross-domain benchmarks (e.g., S3DIS → Semantic3D), our method achieves state-of-the-art generalization performance, significantly improving segmentation accuracy. Experimental results validate that explicit category-level geometric modeling effectively enhances domain-invariant feature learning.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: 3D Computer Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

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.

Problem

• Address domain generalization in 3D point cloud segmentation
• Learn category-level geometric features for better alignment
• Improve model generalization with geometric invariant information

Innovation

• Category-level Geometry Embedding for fine-grained features
• Geometric Consistent Learning aligns category-level embeddings
• Domain-invariant geometric features improve 3D segmentation