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
把 batch 内多个场景点云串行化为连续序列、用状态空间模型做跨样本语义状态传播，为 3D 自监督预训练提供了一种突破「样本独立建模」的新范式；配套的非对称语义保持蒸馏可迁移到任何「预训练依赖 batch 组织、微调却是单样本」的表征学习场景。
原文依据 we propose a PC-SSL framework based on cross-sample semantic propagation (CSP), in which samples within a batch are serialized into continuous input
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论场景级点云自监督学习（PC-SSL）已展现出增强 3D 视觉模型泛化能力的潜力。尽管现有方法推动了该领域的发展，但样本独立建模范式在维持跨场景一致的语义表征方面仍存在显著局限，这一挑战阻碍了统一且可迁移的语义空间的构建。为解决该问题，我们提出了一种基于跨样本语义传播（CSP）的 PC-SSL 框架，其中同一批次内的样本被串行化为连续输入，并由状态空间模型处理以实现语义状态传播。该机制在状态空间中显式建模跨样本的动态依赖关系，使网络能够在潜空间中建立跨样本语义一致性并实现全局语义对齐。由于基于串行化的预训练需要批次级输入组织，我们进一步在微调阶段引入非对称语义保持蒸馏（SPD），以实现语义迁移的结构对齐，并消除由批次依赖所导致的不一致。所提出的 SPD 通过异构输入机制与语义特征对齐约束，确保预训练语义的稳定迁移，使模型在单场景测试条件下仍能保持结构化的语义一致性与鲁棒性。在多个基准数据集上的大量实验表明，我们的方法在性能与语义一致性两方面均持续优于最优方法。
英文原文摘要 1645 字符
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.