Adaptive Non-Rigid Inpainting of 3D Point Cloud Geometry

TL;DR

This paper presents adaptive exemplar-based algorithms for filling large holes in 3D point cloud geometry, improving accuracy and efficiency through adaptive template sizing and non-rigid alignment.

Contribution

The paper introduces novel adaptive template selection and non-rigid transformation techniques for improved 3D point cloud inpainting.

Findings

Higher accuracy in hole filling compared to previous methods

Reduced execution time due to adaptive template sizing

Effective filling of challenging large holes

Abstract

In this letter, we introduce several algorithms for geometry inpainting of 3D point clouds with large holes. The algorithms are examplar-based: hole filling is performed iteratively using templates near the hole boundary to find the best matching regions elsewhere in the cloud, from where existing points are transferred to the hole. We propose two improvements over the previous work on exemplar-based hole filling. The first one is adaptive template size selection in each iteration, which simultaneously leads to higher accuracy and lower execution time. The second improvement is a non-rigid transformation to better align the candidate set of points with the template before the point transfer, which leads to even higher accuracy. We demonstrate the algorithms' ability to fill holes that are difficult or impossible to fill by existing methods.