arXiv 2605.017592026-05-03cs.CV

PointCSP：自监督点云学习中的跨样本语义传播与稳定性保持

PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning

Faculty of Innovation Engineering, Macau University of Science and Technology（澳门科技大学创新工程学院）；Southwest Institute of Technical Physics（西南技术物理研究所）；The Institute of Automation of the Chinese Academy of Sciences（中国科学院自动化研究所）；School of Computing and Information Technology, Great Bay University（湾区大学计算与信息技术学院）

Xinxing Yu, Ajian Liu, Sunyuan Qiang, Hui Ma, Liying Yang, Yuzhong Wang, Zhi Rao, Yanyan Liang

备注：: conference

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

研究点云自监督学习中跨场景语义一致性问题，提出基于跨样本语义传播的PC-SSL框架及非对称语义保持蒸馏，在状态空间显式建模样本动态依赖，实现跨样本语义对齐与稳定转移，实验证明性能优于现有方法。

摘要：

场景级点云自监督学习（PC-SSL）已显示出增强3D视觉模型泛化能力的潜力。尽管现有方法取得了进展，但与样本无关的建模范式在跨场景保持一致语义表示方面仍存在重大局限，阻碍了统一且可转移语义空间的构建。为解决此问题，我们提出基于跨样本语义传播（CSP）的PC-SSL框架，将一批样本序列化作为连续输入，由状态空间模型处理以实现语义状态传播，在潜在空间建立跨样本语义一致性并实现全局语义对齐。由于基于序列化的预训练需要批量输入组织，我们在微调时引入非对称语义保持蒸馏（SPD）以实现语义转移的结构对齐并消除批量依赖导致的不一致。SPD通过异构输入机制和语义特征对齐约束确保预训练语义稳定转移，使模型在单场景测试条件下保持结构化语义一致性和鲁棒性。在多个基准数据集上的大量实验表明，我们的方法在性能和语义一致性上均持续优于现有方法。

英文摘要：

Scene-level point cloud self-supervised learning (PC-SSL) has demonstrated potential in enhancing the generalization capability of 3D vision models. Despite the advances in the field through existing methods, the sample-independent modeling paradigm still poses significant limitations in terms of maintaining consistent semantic representations across scenes. This challenge hinders the construction of a unified and transferable semantic space. To address this issue, we propose a PC-SSL framework based on cross-sample semantic propagation (CSP), in which samples within a batch are serialized into continuous input and processed by a state-space model to enable semantic state propagation. This mechanism explicitly models the dynamic dependencies across samples in the state space, allowing the network to establish cross-sample semantic consistency in the latent space and achieve global semantic alignment. Since serialization-based pretraining requires batch-level input organization, we further introduce an asymmetric semantic preservation distillation (SPD) during finetuning to achieve structural alignment of semantic transfer and eliminate inconsistencies caused by batch dependency. The proposed SPD ensures stable transfer of pretrained semantics through a heterogeneous input mechanism and a semantic feature alignment constraint. This enables the model to maintain structured semantic consistency and robustness under single-scene testing conditions. Extensive experiments on multiple benchmark datasets demonstrate that our method consistently outperforms state-of-the-art methods in both performance and semantic consistency.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。