arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.04891cs.CVcs.CG
收藏

表面重建的层次空间划分

Hierarchical Space Partition for Surface Reconstruction

Independent Researcher(独立研究员);Huazhong University of Science and Technology(华中科技大学)

Minjie Tang, Xiangfei Li

AI总结:

针对点云重建中因LiDAR扫描局限导致细节缺失的问题,提出基于平面分类与优先级生长的层次空间划分方法,并通过最小割优化生成水密多边形网格。

摘要:

从点云生成紧凑的多边形模型是3D视觉和计算机图形学中的一个关键问题。然而,由于LiDAR扫描的固有限制(例如距离约束和遮挡),关键场景信息常常缺失,导致重建精度下降。为了解决这个问题,我们提出了一种平面组装策略,该策略在保持模型紧凑性的同时有效恢复缺失的细节。我们将从场景中提取的所有平面分为三类:高可见、几乎不可见和不可见。通过场景结构分析恢复的不可见平面指示了缺失的细节。这三种类型的平面对应于三种生长优先级。每个平面根据优先级水平生长,空间被逐步划分,即层次划分。随后,我们通过基于最小割的优化从划分中生成水密多边形网格。最后,在公共数据集上的比较显示了我们的方法相对于主流方法的有效性和优越性。项目页面可在https://hsr-3dv.github.io/获取。

英文摘要:

Generating compact polygonal models from point clouds is a key problem in 3D vision and computer graphics. However, due to inherent limitations of LiDAR scanning (e.g. range constraints and occlusions), critical scene information is often missing, leading to degraded reconstruction accuracy. To address this, we propose a plane assembling strategy that effectively recovers missing details while maintaining model compactness. We classify all the planes extracted from the scene into three categories: highly visible, barely visible, and invisible. The invisible planes, which are recovered by scene structure analysis, indicate the missing details. The three types of planes correspond to the three growth priorities. Each plane grows according to the priority level, and the space is partitioned progressively, namely, the hierarchical partition. Subsequently, we generate a watertight polygonal mesh from the partition via a min-cut-based optimization. Finally, comparisons on public datasets show the effectiveness and superiority of our method against mainstream approaches. The project page is available at https://hsr-3dv.github.io/.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑