PPC-MT: Parallel Point Cloud Completion with Mamba-Transformer Hybrid Architecture

TL;DR

PPC-MT introduces a parallel point cloud completion framework using a hybrid Mamba-Transformer architecture, achieving high-quality reconstruction efficiently by leveraging PCA-guided parallel processing and advanced feature modeling.

Contribution

The paper presents a novel parallel completion strategy with a hybrid Mamba-Transformer architecture, improving efficiency and detail fidelity in point cloud reconstruction.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Enhances point distribution uniformity and detail fidelity

Balances computational efficiency with high-quality reconstruction

Abstract

Existing point cloud completion methods struggle to balance high-quality reconstruction with computational efficiency. To address this, we propose PPC-MT, a novel parallel framework for point cloud completion leveraging a hybrid Mamba-Transformer architecture. Our approach introduces an innovative parallel completion strategy guided by Principal Component Analysis (PCA), which imposes a geometrically meaningful structure on unordered point clouds, transforming them into ordered sets and decomposing them into multiple subsets. These subsets are reconstructed in parallel using a multi-head reconstructor. This structured parallel synthesis paradigm significantly enhances the uniformity of point distribution and detail fidelity, while preserving computational efficiency. By integrating Mamba's linear complexity for efficient feature extraction during encoding with the Transformer's capability to model fine-grained multi-sequence relationships during decoding, PPC-MT effectively balances efficiency and reconstruction accuracy. Extensive quantitative and qualitative experiments on benchmark datasets, including PCN, ShapeNet-55/34, and KITTI, demonstrate that PPC-MT outperforms state-of-the-art methods across multiple metrics, validating the efficacy of our proposed framework.