arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.07832cs.CVcs.LG
收藏

LRF-Net:学习局部参考系进行3D局部形状描述和匹配

LRF-Net: Learning Local Reference Frames for 3D Local Shape Description and Matching

Huazhong University of Science and Technology(华中科技大学);Northwestern Polytechnical University(西北工业大学)

Angfan Zhu, Jiaqi Yang, Weiyue Zhao, Zhiguo Cao

摘要:

局部参考系(LRF)在三维局部形状描述和匹配中起着关键作用。然而,大多数现有的LRF都是手工制作的,并且具有有限的可重复性和鲁棒性。本文提出了第一次尝试学习LRF通过暹罗网络,只需要弱监督。特别是,我们认为,在局部表面的每个相邻点给LRF建设和测量通过学习权重的贡献是独一无二的。针对不同应用场景的三个公共数据集的广泛分析和比较实验表明,LRF-Net比几种最先进的LRF方法更具可重复性和鲁棒性(LRF-Net仅在一个数据集上训练)。此外,LRF-Net在匹配3D点云时可以显着提高局部形状描述和6-DoF姿态估计性能。

英文摘要:

The local reference frame (LRF) acts as a critical role in 3D local shape description and matching. However, most of existing LRFs are hand-crafted and suffer from limited repeatability and robustness. This paper presents the first attempt to learn an LRF via a Siamese network that needs weak supervision only. In particular, we argue that each neighboring point in the local surface gives a unique contribution to LRF construction and measure such contributions via learned weights. Extensive analysis and comparative experiments on three public datasets addressing different application scenarios have demonstrated that LRF-Net is more repeatable and robust than several state-of-the-art LRF methods (LRF-Net is only trained on one dataset). In addition, LRF-Net can significantly boost the local shape description and 6-DoF pose estimation performance when matching 3D point clouds.

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。

↑