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

• URL: http://arxiv.org/abs/2508.11265v1
• Date: Fri, 15 Aug 2025 07:02:08 GMT
• Title: Domain-aware Category-level Geometry Learning Segmentation for 3D Point Clouds
• Authors: Pei He, Lingling Li, Licheng Jiao, Ronghua Shang, Fang Liu, Shuang Wang, Xu Liu, Wenping Ma,
• Abstract summary: Category-level Geometry Embedding (CGE) is proposed to perceive the fine-grained geometric properties of point cloud features.<n> Geometric Consistent Learning (GCL) is proposed to simulate the latent 3D distribution and align the category-level geometric embeddings.
• Score: 38.70636648272246
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification [59.17489431187807]
  We propose a framework that enhances 3D geometric fidelity by leveraging CLIP's hierarchical spatial semantics.<n>Our method significantly improves 3D few-shot class-incremental learning, achieving superior geometric coherence and robustness to texture bias.
  arXiv  Detail & Related papers  (2025-09-18T13:45:08Z)
• Geometry Distributions [51.4061133324376]
  We propose a novel geometric data representation that models geometry as distributions. Our approach uses diffusion models with a novel network architecture to learn surface point distributions. We evaluate our representation qualitatively and quantitatively across various object types, demonstrating its effectiveness in achieving high geometric fidelity.
  arXiv  Detail & Related papers  (2024-11-25T04:06:48Z)
• Generalized Few-Shot Point Cloud Segmentation Via Geometric Words [54.32239996417363]
  Few-shot point cloud segmentation algorithms learn to adapt to new classes at the sacrifice of segmentation accuracy for the base classes. We present the first attempt at a more practical paradigm of generalized few-shot point cloud segmentation. We propose the geometric words to represent geometric components shared between the base and novel classes, and incorporate them into a novel geometric-aware semantic representation.
  arXiv  Detail & Related papers  (2023-09-20T11:24:33Z)
• Deep Semantic Graph Matching for Large-scale Outdoor Point Clouds Registration [22.308070598885532]
  We treat the point cloud registration problem as a semantic instance matching and registration task. We propose a deep semantic graph matching method (DeepSGM) for large-scale outdoor point cloud registration. Experimental results conducted on the KITTI Odometry dataset demonstrate that the proposed method improves the registration performance.
  arXiv  Detail & Related papers  (2023-08-10T03:07:28Z)
• Zero-shot point cloud segmentation by transferring geometric primitives [68.18710039217336]
  We investigate zero-shot point cloud semantic segmentation, where the network is trained on seen objects and able to segment unseen objects. We propose a novel framework to learn the geometric primitives shared in seen and unseen categories' objects and employ a fine-grained alignment between language and the learned geometric primitives.
  arXiv  Detail & Related papers  (2022-10-18T15:06:54Z)
• Curved Geometric Networks for Visual Anomaly Recognition [39.91252195360767]
  Learning a latent embedding to understand the underlying nature of data distribution is often formulated in Euclidean spaces with zero curvature. In this work, we investigate benefits of the curved space for analyzing anomalies or out-of-distribution objects in data.
  arXiv  Detail & Related papers  (2022-08-02T01:15:39Z)
• Fitting and recognition of geometric primitives in segmented 3D point clouds using a localized voting procedure [1.8352113484137629]
  We introduce a novel technique for processing point clouds that, through a voting procedure, is able to provide an initial estimate of the primitive parameters each type. By using these estimates we localize the search of the optimal solution in a dimensionally-reduced space, making it efficient to extend the HT to more primitive than those that generally found in the literature.
  arXiv  Detail & Related papers  (2022-05-30T20:47:43Z)
• SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation [94.11915008006483]
  We propose SemAffiNet for point cloud semantic segmentation. We conduct extensive experiments on the ScanNetV2 and NYUv2 datasets.
  arXiv  Detail & Related papers  (2022-05-26T17:00:23Z)
• Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds [36.49322708074682]
  This paper proposes a new method of geometry-aware self-training (GAST) for unsupervised domain adaptation of object point cloud classification. Specifically, this paper aims to learn a domain-shared representation of semantic categories, via two novel self-supervised geometric learning tasks as feature regularization. On the other hand, a diverse point distribution across datasets can be normalized with a novel curvature-aware distortion localization.
  arXiv  Detail & Related papers  (2021-08-20T13:29:11Z)
• Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud [50.56461318879761]
  We propose Geometry-Disentangled Attention Network (GDANet) for 3D image processing. GDANet disentangles point clouds into contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components. Experiments on 3D object classification and segmentation benchmarks demonstrate that GDANet achieves the state-of-the-arts with fewer parameters.
  arXiv  Detail & Related papers  (2020-12-20T13:35:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.