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

TL;DR

PPC-MT is proposed, a novel parallel framework for point cloud completion leveraging a hybrid Mamba-Transformer architecture that effectively balances efficiency and reconstruction accuracy and outperforms state-of-the-art methods across multiple metrics.

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.

Figures (7)

• Figure 1: Illustration of PCA-Guided Decomposition. Target point clouds are first sorted according to Principal Component Analysis (PCA) and then uniformly decomposed into several structured segments.
• Figure 2: The PPCMT framework consists of two primary components: (a) Predicted Point Cloud Generation and (b) Target Point Cloud Decomposition. The Predicted Point Cloud Generation component includes multiple modules, three of which are illustrated in this figure: (c) Feature Extractor, (d) Seed Generator, and (e) Multi-Head Reconstructor.
• Figure 3: The detailed structure of the Mamba Encoder.
• Figure 4: The detailed structure of the Transformer Decoder.
• Figure 5: Qualitative comparison of PCN dataset. All methods above take the point clouds in the first column as inputs. We highlight some regions with red bounding box, which clearly show the effectiveness of our method.