RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging

Abstract

This paper proposes a deep recurrent Rotation Averaging Graph Optimizer (RAGO) for Multiple Rotation Averaging (MRA). Conventional optimization-based methods usually fail to produce accurate results due to corrupted and noisy relative measurements. Recent learning-based approaches regard MRA as a regression problem, while these methods are sensitive to initialization due to the gauge freedom problem. To handle these problems, we propose a learnable iterative graph optimizer minimizing a gauge-invariant cost function with an edge rectification strategy to mitigate the effect of inaccurate measurements. Our graph optimizer iteratively refines the global camera rotations by minimizing each node's single rotation objective function. Besides, our approach iteratively rectifies relative rotations to make them more consistent with the current camera orientations and observed relative rotations. Furthermore, we employ a gated recurrent unit to improve the result by tracing the temporal information of the cost graph. Our framework is a real-time learning-to-optimize rotation averaging graph optimizer with a tiny size deployed for real-world applications. RAGO outperforms previous traditional and deep methods on real-world and synthetic datasets. The code is available at https://github.com/sfu-gruvi-3dv/RAGO

arXiv commentAccepted by CVPR 2022

References in corpus (9)

• Decoupled Weight Decay Regularization
• ORB-SLAM: a Versatile and Accurate Monocular SLAM System
• Neural Message Passing for Quantum Chemistry
• Solving ill-posed inverse problems using iterative deep neural networks
• Learning to Learn without Gradient Descent by Gradient Descent
• BA-Net: Dense Bundle Adjustment Network
• Robust Rotation Synchronization via Low-rank and Sparse Matrix Decomposition
• LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo
• Message Passing Least Squares Framework and its Application to Rotation Synchronization

Cited by in corpus (1)

• Matching Distance and Geometric Distribution Aided Learning Multiview Point Cloud Registration