Convolutional networks are successful due to their equivariance/invariance under translations. However, rotatable data such as images, volumes, shapes, or point clouds require processing with equivariance/invariance under rotations in cases where the rotational orientation of the coordinate system does not affect the meaning of the data (e.g. object classification). On the other hand, estimation/processing of rotations is necessary in cases where rotations are important (e.g. motion estimation). There has been recent progress in methods and theory in all these regards. Here we provide an overview of existing methods, both for 2D and 3D rotations (and translations), and identify commonalities and links between them.
翻译:变迁网络之所以成功,是因为翻译中的变迁/变迁,然而,在协调系统旋转方向不影响数据含义(如物体分类)的情况下,图像、体积、形状或点云等可循环数据需要轮流处理,如图像、体积、形状或点云等易变数据需要轮流处理,在2D和3D旋转(和翻译)不影响数据含义的情况下,则需要估计/处理轮换,而在轮换很重要的情况下,则需要估计/处理轮换(如运动估计),在所有这些方面,方法和理论最近都有进展。在这里,我们概述了现有方法,包括2D和3D旋转(和翻译)的方法,并查明它们之间的共性和联系。