mlsanityData to 7 Oct 2026

TartanAir: A Dataset to Push the Limits of Visual SLAM

arXiv 2003.14338 ↗First posted 31 Mar 2020cs.ROcited by 494

Not on the map. Why?

Cited by 29 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a challenging dataset, the TartanAir, for robot navigation tasks and more. The data is collected in photo-realistic simulation environments with the presence of moving objects, changing light and various weather conditions. By collecting data in simulations, we are able to obtain multi-modal sensor data and precise ground truth labels such as the stereo RGB image, depth image, segmentation, optical flow, camera poses, and LiDAR point cloud. We set up large numbers of environments with various styles and scenes, covering challenging viewpoints and diverse motion patterns that are difficult to achieve by using physical data collection platforms. In order to enable data collection at such a large scale, we develop an automatic pipeline, including mapping, trajectory sampling, data processing, and data verification. We evaluate the impact of various factors on visual SLAM algorithms using our data. The results of state-of-the-art algorithms reveal that the visual SLAM problem is far from solved. Methods that show good performance on established datasets such as KITTI do not perform well in more difficult scenarios. Although we use the simulation, our goal is to push the limits of Visual SLAM algorithms in the real world by providing a challenging benchmark for testing new methods, while also using a large diverse training data for learning-based methods. Our dataset is available at urlhttp://theairlab.org/tartanair-dataset.

Key facts. Cited by 494 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 40; 2023: 48; 2024: 72; 2025: 142; 2026: 173.

494 papers.

Sort:

By area:

  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2024Depth Anything V2cited by 1,385
  3. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  4. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  5. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  6. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  7. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  8. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  9. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  10. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  11. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 356
  12. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 348
38 more
  1. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 324
  2. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  3. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 292
  4. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 290
  5. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  6. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 274
  7. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  8. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 250
  9. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
  10. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 202
  11. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
  12. 2022Deep Patch Visual Odometrycited by 186
  13. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 173
  14. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 170
  15. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 169
  16. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 168
  17. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 165
  18. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 147
  19. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 146
  20. 2023Infinite Photorealistic Worlds using Procedural Generationcited by 142
  21. 2023Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Camerascited by 139
  22. 2025MUSt3R: Multi-view Network for Stereo 3D Reconstructioncited by 139
  23. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 130
  24. 2024Rethinking Inductive Biases for Surface Normal Estimationcited by 122
  25. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
  26. 2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 100
  27. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  28. 2024Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matchingcited by 98
  29. 2022ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wildcited by 90
  30. 2025Easi3R: Estimating Disentangled Motion from DUSt3R Without Trainingcited by 88
  31. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 85
  32. 2025SpatialTrackerV2: 3D Point Tracking Made Easycited by 84
  33. 2024Align3R: Aligned Monocular Depth Estimation for Dynamic Videoscited by 79
  34. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 76
  35. 2022Perspective Fields for Single Image Camera Calibrationcited by 75
  36. 2025Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generationcited by 75
  37. 2022Multi-modal Sensor Fusion for Auto Driving Perception: A Surveycited by 73
  38. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 73

50 most cited of 494 All 494 (JSON)