GASCN: Graph Attention Shape Completion Network

TL;DR

GASCN is a novel neural network that combines graph attention and MLPs to improve shape completion from partial point clouds, outperforming existing methods on benchmark datasets.

Contribution

The paper introduces GASCN, a new shape completion network that integrates local graph-based encoding with global MLP features for more accurate reconstructions.

Findings

GASCN outperforms standard shape completion methods on Shapenet benchmarks.

The model effectively infers local surface normals and extents for dense shape reconstruction.

Experimental results demonstrate improved accuracy over existing approaches.

Abstract

Shape completion, the problem of inferring the complete geometry of an object given a partial point cloud, is an important problem in robotics and computer vision. This paper proposes the Graph Attention Shape Completion Network (GASCN), a novel neural network model that solves this problem. This model combines a graph-based model for encoding local point cloud information with an MLP-based architecture for encoding global information. For each completed point, our model infers the normal and extent of the local surface patch which is used to produce dense yet precise shape completions. We report experiments that demonstrate that GASCN outperforms standard shape completion methods on a standard benchmark drawn from the Shapenet dataset.