%0 Generic %1 wang2020tartanvo %A Wang, Wenshan %A Hu, Yaoyu %A Scherer, Sebastian %D 2020 %K 2020 3D multi-view %T TartanVO: A Generalizable Learning-based VO %U http://arxiv.org/abs/2011.00359 %X 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.

@misc{wang2020tartanvo, abstract = {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.}, added-at = {2021-03-16T07:14:23.000+0100}, author = {Wang, Wenshan and Hu, Yaoyu and Scherer, Sebastian}, biburl = {https://www.bibsonomy.org/bibtex/24ded63044bd88b09cf405750eed13c9e/analyst}, description = {[2011.00359] TartanVO: A Generalizable Learning-based VO}, interhash = {5d8f430fc7254d32dc5a6de09362f083}, intrahash = {4ded63044bd88b09cf405750eed13c9e}, keywords = {2020 3D multi-view}, note = {cite arxiv:2011.00359}, timestamp = {2021-03-16T07:14:23.000+0100}, title = {TartanVO: A Generalizable Learning-based VO}, url = {http://arxiv.org/abs/2011.00359}, year = 2020 }