arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.02786cs.CVcs.AIcs.GR
收藏

基于黎曼 Langevin 动力学的鲁棒对称性检测

Robust Symmetry Detection via Riemannian Langevin Dynamics

Stanford University(斯坦福大学);Technion(以色列理工学院)

Jihyeon Je, Jiayi Liu, Guandao Yang, Boyang Deng, Shengqu Cai, Gordon Wetzstein, Or Litany, Leonidas Guibas

AI总结:

针对噪声及部分对称性检测难题,本文将经典几何投票与生成建模结合,在重定义的黎曼对称空间上使用 Langevin 动力学,实现鲁棒的全局与部分对称性检测并支持下游应用。

摘要:

对称性在自然界和人工创造物中的各类对象上普遍存在。尽管这些对称性在人眼看来可能很直观,但由于搜索空间巨大,用机器检测它们并非易事。经典的基于几何的方法通过聚合针对每种对称性的“投票”来工作,但难以应对噪声。相比之下,基于学习的方法可能对噪声更鲁棒,但由于标注数据稀缺,往往会忽略部分对称性。在这项工作中,我们通过提出一种新颖的对称性检测方法来应对这一挑战,该方法将经典对称性检测技术与生成建模的最新进展相结合。具体而言,我们将 Langevin 动力学应用于重新定义的对称空间,以增强对噪声的鲁棒性。我们在多种形状上提供的实证结果表明,我们的方法不仅对噪声具有鲁棒性,而且能够识别部分对称性和全局对称性。此外,我们还展示了检测到的对称性在压缩和噪声形状对称化等各种下游任务中的效用。

英文摘要:

Symmetries are ubiquitous across all kinds of objects, whether in nature or in man-made creations. While these symmetries may seem intuitive to the human eye, detecting them with a machine is nontrivial due to the vast search space. Classical geometry-based methods work by aggregating "votes" for each symmetry but struggle with noise. In contrast, learning-based methods may be more robust to noise, but often overlook partial symmetries due to the scarcity of annotated data. In this work, we address this challenge by proposing a novel symmetry detection method that marries classical symmetry detection techniques with recent advances in generative modeling. Specifically, we apply Langevin dynamics to a redefined symmetry space to enhance robustness against noise. We provide empirical results on a variety of shapes that suggest our method is not only robust to noise, but can also identify both partial and global symmetries. Moreover, we demonstrate the utility of our detected symmetries in various downstream tasks, such as compression and symmetrization of noisy shapes.

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。

↑