Graph-Guided Deformation for Point Cloud Completion

TL;DR

This paper introduces a novel graph-guided deformation approach for point cloud completion, leveraging GCNs to adapt traditional mesh deformation techniques for improved geometric detail modeling.

Contribution

It presents the first method to refine point cloud completion by mimicking mesh deformation algorithms with GCN-guided deformation, enhancing detail accuracy.

Findings

Outperforms state-of-the-art methods on ShapeNet, KITTI, and Pandar40 datasets.

Effectively models geometric variations through Laplacian deformation simulation.

Demonstrates improved detail preservation in point cloud completion.

Abstract

For a long time, the point cloud completion task has been regarded as a pure generation task. After obtaining the global shape code through the encoder, a complete point cloud is generated using the shape priorly learnt by the networks. However, such models are undesirably biased towards prior average objects and inherently limited to fit geometry details. In this paper, we propose a Graph-Guided Deformation Network, which respectively regards the input data and intermediate generation as controlling and supporting points, and models the optimization guided by a graph convolutional network(GCN) for the point cloud completion task. Our key insight is to simulate the least square Laplacian deformation process via mesh deformation methods, which brings adaptivity for modeling variation in geometry details. By this means, we also reduce the gap between the completion task and the mesh deformation algorithms. As far as we know, we are the first to refine the point cloud completion task by mimicing traditional graphics algorithms with GCN-guided deformation. We have conducted extensive experiments on both the simulated indoor dataset ShapeNet, outdoor dataset KITTI, and our self-collected autonomous driving dataset Pandar40. The results show that our method outperforms the existing state-of-the-art algorithms in the 3D point cloud completion task.