Point cloud completion is a vital task focused on reconstructing complete point clouds and addressing the incompleteness caused by occlusion and limited sensor resolution. Traditional methods relying on fixed local region partitioning, such as k-nearest neighbors, which fail to account for the highly uneven distribution of geometric complexity across different regions of a shape. This limitation leads to inefficient representation and suboptimal reconstruction, especially in areas with fine-grained details or structural discontinuities. This paper proposes a point cloud completion framework called Degree-Flexible Point Graph Completion Network (DFG-PCN). It adaptively assigns node degrees using a detail-aware metric that combines feature variation and curvature, focusing on structurally important regions. We further introduce a geometry-aware graph integration module that uses Manhattan distance for edge aggregation and detail-guided fusion of local and global features to enhance representation. Extensive experiments on multiple benchmark datasets demonstrate that our method consistently outperforms state-of-the-art approaches.
@article{arxiv.2509.23703,
title = {DFG-PCN: Point Cloud Completion with Degree-Flexible Point Graph},
author = {Zhenyu Shu and Jian Yao and Shiqing Xin},
journal= {arXiv preprint arXiv:2509.23703},
year = {2025}
}