TartanVO: A Generalizable Learning-based VO
About
We present the first learning-based visual odometry (VO) model, which generalizes to multiple datasets and real-world scenarios and outperforms geometry-based methods in challenging scenes. We achieve this by leveraging the SLAM dataset TartanAir, which provides a large amount of diverse synthetic data in challenging environments. Furthermore, to make our VO model generalize across datasets, we propose an up-to-scale loss function and incorporate the camera intrinsic parameters into the model. Experiments show that a single model, TartanVO, trained only on synthetic data, without any finetuning, can be generalized to real-world datasets such as KITTI and EuRoC, demonstrating significant advantages over the geometry-based methods on challenging trajectories. Our code is available at https://github.com/castacks/tartanvo.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Visual-Inertial Odometry | EuRoC (All sequences) | MH1 Error0.639 | 69 | |
| SLAM | M3DGR | Average Rank8.5 | 68 | |
| Visual Odometry | KITTI | KITTI Seq 03 Error2.7 | 45 | |
| Visual Odometry | TUM-RGBD | freiburg1/desk2 Error0.122 | 43 | |
| Visual Odometry | KITTI Seq. 10 | Translational Error (%)6.89 | 35 | |
| Camera pose estimation | TUM freiburg1 | Rotation Error0.049 | 34 | |
| Visual Odometry | KITTI Odometry official (sequences 00-10) | Sequence 10 Error11.9 | 25 | |
| Camera pose estimation | Sintel 14-sequence | ATE23.8 | 24 | |
| Visual Odometry | TartanAir (test) | Error MH0002.12 | 19 | |
| Visual-Inertial Odometry | EuRoC MAV | Average Error0.68 | 19 |