# Point Cloud Completion Network Based on Multi-Dimensional Adaptive Feature Fusion and Informative Channel Attention Mechanism

## TL;DR

This paper introduces a new point cloud completion network that improves the reconstruction of missing 3D data by combining local and global features with an attention mechanism.

## Contribution

The novel FFPF-Net with SCMP and SEP-Net modules enhances point cloud completion by capturing both local and global features and refining missing regions.

## Key findings

- The proposed network achieved average prediction error improvements of 1.3 and 1.4 over existing methods.
- The average completion errors on ShapeNet-Part and MVP datasets were 0.783 and 0.824, respectively.
- The method demonstrates improved fine-detail reconstruction and overall data integrity.

## Abstract

With the continuous advancement of 3D perception technology, point cloud data has found increasingly widespread application. However, the presence of holes in point cloud data caused by device limitations and environmental interference severely restricts algorithmic performance, making point cloud completion a research topic of high interest. This study observes that most existing mainstream point cloud completion methods primarily focus on capturing global features, while often underrepresenting local structural details. Moreover, the generation process of complete point clouds lacks effective control over fine-grained features, leading to insufficient detail in the completed outputs and reduced data integrity. To address these issues, we propose a Set Combination Multi-Layer Perceptron (SCMP) module that enables the simultaneous extraction of both local and global features, thereby reducing the loss of local detail information. In addition, we introduce the Squeeze Excitation Pooling Network (SEP-Net) module, an informative channel attention mechanism capable of adaptively identifying and enhancing critical channel features, thus improving the overall feature representation capability. Based on these modules, we further design a novel Feature Fusion Point Fractal Network (FFPF-Net), which fuses multi-dimensional point cloud features to enhance representation capacity and progressively refines the missing regions to generate a more complete point cloud. Extensive experiments conducted on the ShapeNet-Part and MVP datasets compared to L-GAN and PCN showed average prediction error improvements of 1.3 and 1.4, respectively. The average completion errors on the ShapeNet-Part and MVP datasets are 0.783 and 0.824, highlighting the improved fine-detail reconstruction capability of our network. These results indicate that the proposed method effectively enhances point cloud completion performance and can further promote the practical application of point cloud data in various real-world scenarios.