Abstract | ||
---|---|---|
Dense image alignment from RGB-D images remains a critical issue for real-world applications, especially under challenging lighting conditions and in a wide baseline setting. In this letter, we propose a new framework to learn a pixel-wise deep feature map and a deep feature-metric uncertainty map predicted by a Convolutional Neural Network (CNN), which together formulate a deep probabilistic feature-metric residual of the two-view constraint that can be minimised using Gauss-Newton in a coarse-to-fine optimisation framework. Furthermore, our network predicts a deep initial pose for faster and more reliable convergence. The optimisation steps are differentiable and unrolled to train in an end-to-end fashion. Due to its probabilistic essence, our approach can easily couple with other residuals, where we show a combination with ICP. Experimental results demonstrate state-of-the-art performances on the TUM RGB-D dataset and the 3D rigid object tracking dataset. We further demonstrate our method's robustness and convergence qualitatively. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/LRA.2020.3039216 | IEEE Robotics and Automation Letters |
Keywords | DocType | Volume |
Deep learning for visual perception,SLAM | Journal | 6 |
Issue | ISSN | Citations |
1 | 2377-3766 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xu Binbin | 1 | 3 | 1.47 |
Andrew J. Davison | 2 | 6707 | 350.85 |
Stefan Leutenegger | 3 | 1379 | 61.81 |