Edge Preserving Implicit Surface Representation of Point Clouds

TL;DR

This paper introduces an edge-preserving implicit surface reconstruction method from point clouds that maintains sharp features and improves 3D reconstruction quality, especially with lower-quality data.

Contribution

It proposes a novel combination of a differentiable Laplacian regularizer and a dynamic edge sampling strategy for improved surface reconstruction.

Findings

Significantly better reconstruction quality compared to state-of-the-art methods.

Effective preservation of sharp edges in reconstructed surfaces.

Applicable to point cloud analysis tasks like edge feature extraction and normal estimation.

Abstract

Learning implicit surface directly from raw data recently has become a very attractive representation method for 3D reconstruction tasks due to its excellent performance. However, as the raw data quality deteriorates, the implicit functions often lead to unsatisfactory reconstruction results. To this end, we propose a novel edge-preserving implicit surface reconstruction method, which mainly consists of a differentiable Laplican regularizer and a dynamic edge sampling strategy. Among them, the differential Laplican regularizer can effectively alleviate the implicit surface unsmoothness caused by the point cloud quality deteriorates; Meanwhile, in order to reduce the excessive smoothing at the edge regions of implicit suface, we proposed a dynamic edge extract strategy for sampling near the sharp edge of point cloud, which can effectively avoid the Laplacian regularizer from smoothing all regions. Finally, we combine them with a simple regularization term for robust implicit surface reconstruction. Compared with the state-of-the-art methods, experimental results show that our method significantly improves the quality of 3D reconstruction results. Moreover, we demonstrate through several experiments that our method can be conveniently and effectively applied to some point cloud analysis tasks, including point cloud edge feature extraction, normal estimation,etc.