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

2025-08-15 · Pei He, Lingling Li, Licheng Jiao, Ronghua Shang, Fang Liu, Shuang Wang, Xu Liu, Wenping Ma arxiv

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.

📄 PDF Abstract BibTeX arXiv:2508.11265

Code (0)

등록된 구현이 없습니다.

Tasks

3D Semantic Segmentation Domain Generalization Point Clouds

SCAPO: Self-Supervised Category-Level Articulated Pose Estimation from a Single 3D Observation

2026-06-01 · Can Zhang, Gim Hee Lee arxiv

Existing methods for category-level object articulation from a single 3D observation often rely on dense supervision, multi-frame inputs, or CAD templates, and still struggle to disentangle geometry from articulation or …

Pose Estimation

Domain Adaptive Nuclei Instance Segmentation and Classification via Category-aware Feature Alignment and Pseudo-labelling

2022-07-04 · Canran Li, Dongnan Liu, Haoran Li, Zheng Zhang 외

Unsupervised domain adaptation (UDA) methods have been broadly utilized to improve the models' adaptation ability in general computer vision. However, different from the natural images, there exist huge semantic gaps for…

Classification Domain Adaptation Instance Segmentation Segmentation+2

MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detection

2025-05-04 · Jiayi Cheng, Can Gao, Jie zhou, Jiajun Wen 외

3D Anomaly Detection (AD) is a promising means of controlling the quality of manufactured products. However, existing methods typically require carefully training a task-specific model for each category independently, le…

3D Anomaly Detection Anomaly Detection

Semantic-Aware Domain Generalized Segmentation

2022-04-02 · CVPR 2022 1 · Duo Peng, Yinjie Lei, Munawar Hayat, Yulan Guo 외

Deep models trained on source domain lack generalization when evaluated on unseen target domains with different data distributions. The problem becomes even more pronounced when we have no access to target domain samples…

Domain Generalization Segmentation Semantic Segmentation

Geometry-Aware Distillation for Indoor Semantic Segmentation

2019-06-01 · CVPR 2019 6 · Jianbo Jiao, Yunchao Wei, Zequn Jie, Honghui Shi 외

It has been shown that jointly reasoning the 2D appearance and 3D information from RGB-D domains is beneficial to indoor scene semantic segmentation. However, most existing approaches require accurate depth map as input …

Segmentation Semantic Segmentation