Morphing and Sampling Network for Dense Point Cloud Completion

TL;DR

This paper introduces a two-stage network for dense 3D point cloud completion that predicts a coarse shape and refines it through a novel sampling process, improving detail and structural accuracy.

Contribution

The proposed method uniquely combines parametric surface prediction with a new sampling algorithm for enhanced dense point cloud completion.

Findings

Outperforms existing methods in EMD and CD metrics

Effectively preserves structural details and avoids uneven distribution

Demonstrates high-fidelity dense point cloud reconstruction

Abstract

3D point cloud completion, the task of inferring the complete geometric shape from a partial point cloud, has been attracting attention in the community. For acquiring high-fidelity dense point clouds and avoiding uneven distribution, blurred details, or structural loss of existing methods' results, we propose a novel approach to complete the partial point cloud in two stages. Specifically, in the first stage, the approach predicts a complete but coarse-grained point cloud with a collection of parametric surface elements. Then, in the second stage, it merges the coarse-grained prediction with the input point cloud by a novel sampling algorithm. Our method utilizes a joint loss function to guide the distribution of the points. Extensive experiments verify the effectiveness of our method and demonstrate that it outperforms the existing methods in both the Earth Mover's Distance (EMD) and the Chamfer Distance (CD).