mlsanityData to 14 Oct 2026

TartanVO: A Generalizable Learning-based VO

arXiv 2011.00359 ↗First posted 31 Oct 2020cs.CV cs.LG cs.ROcited by 108

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 108 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 16; 2023: 16; 2024: 31; 2025: 25; 2026: 16.

108 papers.

Sort:

By area:

  1. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  2. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  3. 2022Deep Patch Visual Odometrycited by 190
  4. 2023Infinite Photorealistic Worlds using Procedural Generationcited by 147
  5. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 137
  6. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 103
  7. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  8. 2022ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wildcited by 92
  9. 2024Deep Patch Visual SLAMcited by 71
  10. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
  11. 2024LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometrycited by 56
  12. 2023Dense RGB SLAM with Neural Implicit Mapscited by 42
38 more
  1. 2022The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTscited by 38
  2. 2023Deep Event Visual Odometrycited by 29
  3. 2022DiffPoseNet: Direct Differentiable Camera Pose Estimationcited by 27
  4. 2022DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environmentscited by 27
  5. 2022How Does It Feel? Self-Supervised Costmap Learning for Off-Road Vehicle Traversabilitycited by 27
  6. 2025Dynamic Camera Poses and Where to Find Themcited by 27
  7. 2022PVO: Panoptic Visual Odometrycited by 26
  8. 2022PlaneFormers: From Sparse View Planes to 3D Reconstructioncited by 26
  9. 2024DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignmentcited by 26
  10. 2025Back on Track: Bundle Adjustment for Dynamic Scene Reconstructioncited by 24
  11. 2025Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representationcited by 23
  12. 2023Deep Learning for Camera Calibration and Beyond: A Surveycited by 20
  13. 2024MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometrycited by 19
  14. 2023XVO: Generalized Visual Odometry via Cross-Modal Self-Trainingcited by 18
  15. 2023Learning a Depth Covariance Functioncited by 16
  16. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
  17. 2023iSLAM: Imperative SLAMcited by 15
  18. 2024Fast Encoder-Based 3D from Casual Videos via Point Track Processingcited by 14
  19. 2024Reinforcement Learning Meets Visual Odometrycited by 14
  20. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 14
  21. 2024FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimationcited by 12
  22. 2025L4P: Towards Unified Low-Level 4D Vision Perceptioncited by 12
  23. 20213D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Videocited by 11
  24. 20234DRVO-Net: Deep 4D Radar-Visual Odometry Using Multi-Modal and Multi-Scale Adaptive Fusioncited by 11
  25. 2023SuperPrimitive: Scene Reconstruction at a Primitive Levelcited by 11
  26. 2023NeRF-VO: Real-Time Sparse Visual Odometry with Neural Radiance Fieldscited by 10
  27. 2022D3FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidancecited by 9
  28. 2023DVI-SLAM: A Dual Visual Inertial SLAM Networkcited by 9
  29. 2023VoxDet: Voxel Learning for Novel Instance Detectioncited by 8
  30. 2024Generating Diverse Agricultural Data for Vision-Based Farming Applicationscited by 7
  31. 2021MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraintscited by 6
  32. 2022Physical Passive Patch Adversarial Attacks on Visual Odometry Systemscited by 6
  33. 2023Synthetic Data-based Detection of Zebras in Drone Imagerycited by 6
  34. 2023Loss it right: Euclidean and Riemannian Metrics in Learning-based Visual Odometrycited by 6
  35. 2024Customizable Perturbation Synthesis for Robust SLAM Benchmarkingcited by 6
  36. 2025VIGS-SLAM: Visual Inertial Gaussian Splatting SLAMcited by 6
  37. 2024MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothingcited by 5
  38. 2025Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Imagecited by 5

50 most cited of 108 All 108 (JSON)