RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging
About
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
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Multiple Rotation Averaging | Synthetic Dataset (test) | Mean Angular Error0.23 | 18 | |
| Rotation Averaging | 1DSfM Alamo 1.0 | Mean Angular Error2.82 | 6 | |
| Rotation Averaging | 1DSfM 1.0 (Ellis Island) | Mean Angular Error1.74 | 6 | |
| Rotation Averaging | 1DSfM 1.0 (Montreal Notre Dame) | Mean Angular Error0.86 | 6 | |
| Rotation Averaging | 1DSfM Piazza del Popolo 1.0 | Mean Angular Error1.91 | 6 | |
| Rotation Averaging | 1DSfM Tower of London 1.0 | Mean Angular Error (mn)2.51 | 6 | |
| Rotation Averaging | 1DSfM Yorkminster 1.0 | Mean Angular Error2.18 | 6 | |
| Rotation Averaging | 1DSfM Piccadilly 1.0 | Mean Angular Error2.44 | 6 | |
| Rotation Averaging | 1DSfM Gendarmenmarkt 1.0 | Mean Angular Error (mn)5.24 | 6 | |
| Rotation Averaging | 1DSfM Union Square 1.0 | Mean Angular Error4.68 | 6 |