Current semantic segmentation approaches for point cloud scenes heavily rely on manual labeling, while research on unsupervised semantic segmentation methods specifically for raw point clouds is still in its early stages. Unsupervised point cloud learning poses significant challenges due to the absence of annotation information and the lack of pre-training. The development of effective strategies is crucial in this context. In this paper, we propose a novel prototype library-driven unsupervised point cloud semantic segmentation strategy that utilizes Structure Learning and Consistent Reasoning (P-SLCR). First, we propose a Consistent Structure Learning to establish structural feature learning between consistent points and the library of consistent prototypes by selecting high-quality features. Second, we propose a Semantic Relation Consistent Reasoning that constructs a prototype inter-relation matrix between consistent and ambiguous prototype libraries separately. This process ensures the preservation of semantic consistency by imposing constraints on consistent and ambiguous prototype libraries through the prototype inter-relation matrix. Finally, our method was extensively evaluated on the S3DIS, SemanticKITTI, and Scannet datasets, achieving the best performance compared to unsupervised methods. Specifically, the mIoU of 47.1% is achieved for Area-5 of the S3DIS dataset, surpassing the classical fully supervised method PointNet by 2.5%.

Weakly-supervised point cloud semantic segmentation (WS-PCS) has attracted increasing attention due to the challenge of sparse annotations. A central problem is how to effectively extract informative features from the annotated points, enabling reliable supervision. Although many existing works extend 2D graph convolution to 3D point cloud data, 2D convolution inherently assumes feature localization, which is an assumption that does not hold in point clouds, and lacks consistent semantic offsets. To address this, we propose a novel Bilateral Graph Convolutional (BGC) method, which refines graph edges into two categories: regular edges and offset edges, providing improved guidance for WS-PCS. Firstly, we create the Local Bilateral Relations (LBR) module to learn the relational features of edges in local point cloud graphs, encompassing both regular and offset edges. To the best of our knowledge, we are the first to utilize offset edges to capture irregular semantic offsets in point cloud data. Secondly, we propose the Adaptive Pooling (AP) module, which adaptively pools edge information learned from LBR, enhancing the feature characterization ability by incorporating salient and pervasive features. Finally, we design BGC as BGC-Net and evaluate its performance against recent networks on four datasets, achieving state-of-the-art results.

Semantic segmentation of large-scale point clouds under weak supervision is challenging due to the limited annotations. Current methods typically rely on the implicit use of annotation information to supervise the network, thereby constraining the capacity to characterize features at annotation points. In this article, we propose a query points component reasoning (QPCR) framework, which enhances the utilization of annotation information by introducing them into the middle layer, thereby refining the features used for semantic segmentation. First, we propose the semantic annotations component code reasoning (SACC Reasoning) module, which uses annotations of query points to supervise the semantic information of gradual query points. The semantic annotations component code (SACC) Reasoning module can guide the learning of feature representations of semantic annotations at multiple scales. Second, we create the semantic primitive component code reasoning (SPCC Reasoning) module, which addresses the issue of supervising the network using existing annotation point information that may suppress active features. The semantic primitive component code (SPCC) Reasoning module infers semantic primitive labels of query points using the decoding layer and uses them to guide the corresponding coding layer in learning semantic primitives. Finally, our QPCR method achieves state-of-the-art (SOTA) results on public benchmark datasets. Specifically, even with only 1% of annotated points, our QPCR method achieves the highest mIoU accuracy, i.e., 65.4% on S3DIS Area 5, 56.4% on SensatUrban and 55.3% mIoU on SemanticKITTI, respectively.

Graph self-supervised learning is a task replete with potential. Previously, mainstream approaches in graph self-supervised learning were based on contrastive or generative tasks to extract graph embeddings, achieving commendable performance in downstream tasks such as node classification. However, these two methods have their respective strengths and limitations: (i) contrastive graph learning excels at capturing discriminative features of the graph but is more prone to overlooking structural representations of the graph itself; (ii) generative methods prioritize learning reconstructive features but struggle with large graphs and are susceptible to overfitting. Consequently, several simplistic fusion methods have been proposed, integrating encoded features from both approaches through concatenation, addition, or attention mechanisms for downstream tasks. However, these methods tend to be overly coarse, neglecting some unique information present in both categories of methods.To enhance the synergy of these two methods, we propose an edge perturbation data augmentation method to prevent the generation of spurious positive samples and a feature imputation decoder to complement contrastive features. We assess the model’s performance on two downstream tasks in graph representation learning, and experimental results demonstrate that our proposed method outperforms baseline methods on ten publicly available datasets.