arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.00347cs.CV
收藏

E$^3$-Net:高效的 E(3)-等变法线估计网络

E$^3$-Net: Efficient E(3)-Equivariant Normal Estimation Network

CASIA(中国科学院自动化研究所);HKISI(香港中文大学信息工程学院);KAUST(阿卜杜拉国王科技大学)

Hanxiao Wang, Mingyang Zhao, Weize Quan, Zhen Chen, Dong-ming Yan, Peter Wonka

AI总结:

针对点云法线估计中忽略等变性导致对称模式学习低效的问题,提出 E3-Net,通过引入随机标架方法、高斯加权损失和感知感受野的推理策略,在大幅降低训练资源的同时显著提升了估计精度。

摘要:

点云法线估计是三维几何处理中的一项基础任务。尽管近期基于学习的方法在法线预测方面取得了显著进展,但它们往往忽略了等变性这一关键方面。这导致了对对称模式的学习效率低下。为了解决这一问题,我们提出了 E3-Net 以实现法线估计的等变性。我们引入了一种高效的随机标架方法,该方法将此任务所需的训练资源显著降低至先前工作的 1/8,并提升了精度。此外,我们设计了高斯加权损失函数和一种感知感受野的推理策略,从而有效利用了点云的局部属性。我们的方法在合成数据集和真实数据集上均取得了优异的结果,并以显著优势超越了当前最先进的技术:在 PCPNet 数据集上将 RMSE 降低了 4%,在 SceneNN 数据集上降低了 7%,在 famousShape 数据集上降低了 44%。

英文摘要:

Point cloud normal estimation is a fundamental task in 3D geometry processing. While recent learning-based methods achieve notable advancements in normal prediction, they often overlook the critical aspect of equivariance. This results in inefficient learning of symmetric patterns. To address this issue, we propose E3-Net to achieve equivariance for normal estimation. We introduce an efficient random frame method, which significantly reduces the training resources required for this task to just 1/8 of previous work and improves the accuracy. Further, we design a Gaussian-weighted loss function and a receptive-aware inference strategy that effectively utilizes the local properties of point clouds. Our method achieves superior results on both synthetic and real-world datasets, and outperforms current state-of-the-art techniques by a substantial margin. We improve RMSE by 4% on the PCPNet dataset, 2.67% on the SceneNN dataset, and 2.44% on the FamousShape dataset.

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。

↑