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
2.24%, 0.87%, and 0.94% in performance on the three variants of ScanObjectNN
while reducing parameters by 88% and computation by 73%.

提出了一种基于局部约束紧凑编码器和局部约束 Mamba 解码器的局部约束紧凑点云模型 (LCM)，它在性能和效率方面显著超越了现有的基于 Transformer 的模型，尤其是在 ScanObjectNN 的三个变体上，相比于基于 Transformer 的模型，在性能上改进了 2.24%、0.87% 和 0.94%，同时减少了 88% 的参数和 73% 的计算。