RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging
This work addresses a key challenge in 3D reconstruction and SLAM for robotics and AR/VR applications, offering a real-time, deployable solution with improved accuracy over existing methods.
The paper tackles the problem of Multiple Rotation Averaging (MRA) in computer vision, which often suffers from inaccurate results due to noisy measurements and gauge freedom issues, by proposing RAGO, a deep recurrent graph optimizer that iteratively refines camera rotations and rectifies relative rotations, achieving state-of-the-art performance on real-world and synthetic datasets.
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