arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.02101cs.CVcs.LG
收藏

对称鲁棒的3D方向估计

Symmetry-Robust 3D Orientation Estimation

MIT CSAIL

Christopher Scarvelis, David Benhaim, Paul Zhang

AI总结:

本文提出一种两阶段方向估计流水线,针对旋转对称形状的对称性问题实现鲁棒的3D完整方向估计,并在整个Shapenet上取得上轴估计的最先进性能。

摘要:

方向估计是3D形状分析中的一项基础任务,其内容是估计形状的方向轴:侧轴、上轴和前轴。利用这些数据,可以将形状旋转到规范方向,使其方向轴与坐标轴对齐。开发一种能够可靠估计一般形状完整方向的方向算法仍然是一个未解决的问题。我们引入了一个两阶段方向流水线,在上轴估计上取得了最先进的性能,并进一步证明了其在完整方向估计(即同时求解三个方向轴)上的有效性。与以往工作不同,我们在整个Shapenet数据集上训练和评估我们的方法,而不是仅在部分类别子集上。我们通过描述旋转对称形状方向估计根本障碍的理论来论证我们的工程贡献,并展示了我们的方法如何避免这些障碍。

英文摘要:

Orientation estimation is a fundamental task in 3D shape analysis which consists of estimating a shape's orientation axes: its side-, up-, and front-axes. Using this data, one can rotate a shape into canonical orientation, where its orientation axes are aligned with the coordinate axes. Developing an orientation algorithm that reliably estimates complete orientations of general shapes remains an open problem. We introduce a two-stage orientation pipeline that achieves state of the art performance on up-axis estimation and further demonstrate its efficacy on full-orientation estimation, where one seeks all three orientation axes. Unlike previous work, we train and evaluate our method on all of Shapenet rather than a subset of classes. We motivate our engineering contributions by theory describing fundamental obstacles to orientation estimation for rotationally-symmetric shapes, and show how our method avoids these obstacles.

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。

↑