LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling

TL;DR

This paper introduces LCM, a locally constrained compact point cloud model that replaces traditional Transformer components with local aggregation and Mamba-based decoders, achieving higher efficiency and better performance in masked point modeling tasks.

Contribution

The paper proposes a novel LCM framework with local aggregation and Mamba-based decoders, reducing complexity and parameters while improving accuracy over Transformer-based models.

Findings

Achieved 1.84% higher accuracy on ScanObjectNN variants.

Reduced model parameters by 88% and computation by 73%.

Outperformed existing Transformer-based models in efficiency and accuracy.

Abstract

The pre-trained point cloud model based on Masked Point Modeling (MPM) has exhibited substantial improvements across various tasks. However, these models heavily rely on the Transformer, leading to quadratic complexity and limited decoder, hindering their practice application. To address this limitation, we first conduct a comprehensive analysis of existing Transformer-based MPM, emphasizing the idea that redundancy reduction is crucial for point cloud analysis. To this end, we propose a Locally constrained Compact point cloud Model (LCM) consisting of a locally constrained compact encoder and a locally constrained Mamba-based decoder. Our encoder replaces self-attention with our local aggregation layers to achieve an elegant balance between performance and efficiency. Considering the varying information density between masked and unmasked patches in the decoder inputs of MPM, we introduce a locally constrained Mamba-based decoder. This decoder ensures linear complexity while maximizing the perception of point cloud geometry information from unmasked patches with higher information density. Extensive experimental results show that our compact model significantly surpasses existing Transformer-based models in both performance and efficiency, especially our LCM-based Point-MAE model, compared to the Transformer-based model, achieved an improvement of 1.84%, 0.67%, and 0.60% in average accuracy on the three variants of ScanObjectNN while reducing parameters by 88% and computation by 73%. Code is available at https://github.com/zyh16143998882/LCM.