Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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.

Wenshan Wang, Yaoyu Hu, Sebastian Scherer• 2020

Related benchmarks

TaskDatasetResultRank
Visual-Inertial OdometryEuRoC (All sequences)
MH1 Error0.639
51
Camera pose estimationTUM freiburg1
Rotation Error0.049
34
Visual OdometryTUM-RGBD
freiburg1/xyz Error0.062
34
Camera pose estimationSintel 14-sequence
ATE23.8
15
TrackingEuRoC Dataset
MH 01 Score63.9
13
Monocular SLAMEuRoC (test)
ATE Error (MH03)0.55
12
Camera pose estimationMPI Sintel
ATE (m)0.238
11
Visual OdometryTartanAir (test)
Error MH0004.88
11
Simultaneous Localization and Mapping (SLAM)TUM-RGBD (various sequences)
Error Desk0.125
8
Visual OdometrynuScenes 12Hz (unseen regions)
Translation Error (m)10.27
8
Showing 10 of 15 rows

Other info

Follow for update