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

TL;DR

PointCSP introduces a novel self-supervised learning framework for point clouds that enhances semantic consistency across samples and improves robustness in 3D vision tasks.

Contribution

It proposes cross-sample semantic propagation and an asymmetric semantic preservation distillation to achieve global semantic alignment and stability.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Achieves more consistent semantic representations across scenes.

Enhances robustness in single-scene testing conditions.

Abstract

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.