Tangent Space Backpropagation for 3D Transformation Groups
arXiv:2103.12032
Abstract
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.
arXiv commentfixed typos
References in corpus (9)
- Manopt, a Matlab toolbox for optimization on manifolds
- A micro Lie theory for state estimation in robotics
- DeepV2D: Video to Depth with Differentiable Structure from Motion
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
- BA-Net: Dense Bundle Adjustment Network
- Accelerating 3D Deep Learning with PyTorch3D
- TartanAir: A Dataset to Push the Limits of Visual SLAM
- McTorch, a manifold optimization library for deep learning
- Consistent Video Depth Estimation