Tangent Space Backpropagation for 3D Transformation Groups

Tangent Space Backpropagation for 3D Transformation Groups
复制标题

DOI:
10.1109/cvpr46437.2021.01020
复制
发表时间:
2021-03
期刊:
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子:
--
通讯作者:
Zachary Teed;Jia Deng
Zachary Teed;Jia Deng
中科院分区:
其他
文献类型:
--
作者:
Zachary Teed;Jia Deng

文献摘要

相似文献

我们解决了涉及3D变换群SO(3),SE(3)和Sim(3)的计算图的反向传播问题。3D变换群广泛用于3D视觉和机器人技术,但它们不形成向量空间,而是位于光滑流形上。标准的反向传播方法,其中嵌入3D变换在欧几里德空间,遭受数值困难。我们引入了一个新的库,它利用了3D变换的群结构,并在流形的切空间中进行反向传播。我们表明,我们的方法是数字上更稳定,更容易实现,并有利于一组不同的任务。我们的即插即用PyTorch库可在https://github.com/princeton-vl/lietorch上找到。
We address the problem of performing backpropagation for computation graphs involving 3D transformation groups SO(3), SE(3), and Sim(3). 3D transformation groups are widely used in 3D vision and robotics, but they do not form vector spaces and instead lie on smooth manifolds. The standard backpropagation approach, which embeds 3D transformations in Euclidean spaces, suffers from numerical difficulties. We introduce a new library, which exploits the group structure of 3D transformations and performs backpropagation in the tangent spaces of manifolds. We show that our approach is numerically more stable, easier to implement, and beneficial to a diverse set of tasks. Our plug-and-play PyTorch library is available at https://github.com/princeton-vl/lietorch.