mlsanityData to 7 Oct 2026

UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning

arXiv 1709.06841 ↗First posted 20 Sep 2017cs.CVcited by 95

Not on the map. Why?

Abstract (arXiv)

We propose a novel monocular visual odometry (VO) system called UnDeepVO in this paper. UnDeepVO is able to estimate the 6-DoF pose of a monocular camera and the depth of its view by using deep neural networks. There are two salient features of the proposed UnDeepVO: one is the unsupervised deep learning scheme, and the other is the absolute scale recovery. Specifically, we train UnDeepVO by using stereo image pairs to recover the scale but test it by using consecutive monocular images. Thus, UnDeepVO is a monocular system. The loss function defined for training the networks is based on spatial and temporal dense information. A system overview is shown in Fig. 1. The experiments on KITTI dataset show our UnDeepVO achieves good performance in terms of pose accuracy.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Sep 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 21; 2023: 18; 2024: 11; 2025: 12; 2026: 4.

95 papers.

Sort:

By area:

  1. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  2. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  3. 2021Monocular 3D Object Detection: An Extrinsic Parameter Free Approachcited by 69
  4. 2024Deep Patch Visual SLAMcited by 68
  5. 2022Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depthcited by 48
  6. 2021Full Surround Monodepth from Multiple Camerascited by 41
  7. 2021Differentiable SLAM-net: Learning Particle SLAM for Visual Navigationcited by 34
  8. 2022DiffPoseNet: Direct Differentiable Camera Pose Estimationcited by 27
  9. 2022MGNet: Monocular Geometric Scene Understanding for Autonomous Drivingcited by 27
  10. 2021Attentive and Contrastive Learning for Joint Depth and Motion Field Estimationcited by 24
  11. 2022When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimationcited by 24
  12. 2021DF-VO: What Should Be Learnt for Visual Odometry?cited by 22
38 more
  1. 2021LIFT-SLAM: a deep-learning feature-based monocular visual SLAM methodcited by 20
  2. 2023Deep Learning for Camera Calibration and Beyond: A Surveycited by 20
  3. 2024MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometrycited by 19
  4. 2022Improving Monocular Visual Odometry Using Learned Depthcited by 17
  5. 2023XVO: Generalized Visual Odometry via Cross-Modal Self-Trainingcited by 17
  6. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
  7. 2021From SLAM to Situational Awareness: Challenges and Surveycited by 14
  8. 2023iSLAM: Imperative SLAMcited by 14
  9. 2023Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Networkcited by 14
  10. 2023Deep Learning for Visual Localization and Mapping: A Surveycited by 14
  11. 2021Advancing Self-supervised Monocular Depth Learning with Sparse LiDARcited by 13
  12. 2023Lightweight, Uncertainty-Aware Conformalized Visual Odometrycited by 13
  13. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 13
  14. 2021Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networkscited by 12
  15. 2021H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometrycited by 12
  16. 2022JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenescited by 11
  17. 2021Self-supervised Visual-LiDAR Odometry with Flip Consistencycited by 9
  18. 2021Deep Online Correction for Monocular Visual Odometrycited by 9
  19. 2021Moving SLAM: Fully Unsupervised Deep Learning in Non-Rigid Scenescited by 8
  20. 2022GeoRefine: Self-Supervised Online Depth Refinement for Accurate Dense Mappingcited by 8
  21. 2023Transformer-Based Model for Monocular Visual Odometry: A Video Understanding Approachcited by 8
  22. 2024SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learningcited by 7
  23. 2021Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple Maskscited by 6
  24. 2021DeepAVO: Efficient Pose Refining with Feature Distilling for Deep Visual Odometrycited by 6
  25. 2021MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraintscited by 6
  26. 2021MDN-VO: Estimating Visual Odometry with Confidencecited by 6
  27. 2022Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modelingcited by 6
  28. 2022Self-Supervised Ego-Motion Estimation Based on Multi-Layer Fusion of RGB and Inferred Depthcited by 6
  29. 2022EMA-VIO: Deep Visual-Inertial Odometry with External Memory Attentioncited by 6
  30. 2023FMapping: Factorized Efficient Neural Field Mapping for Real-Time Dense RGB SLAMcited by 6
  31. 2021Unsupervised Joint Learning of Depth, Optical Flow, Ego-motion from Videocited by 5
  32. 2023Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation: A Comprehensive Reviewcited by 5
  33. 2024MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothingcited by 5
  34. 2021Unsupervised Monocular Depth Perception: Focusing on Moving Objectscited by 4
  35. 2022CUAHN-VIO: Content-and-Uncertainty-Aware Homography Network for Visual-Inertial Odometrycited by 4
  36. 2023Generalizable End-to-End Deep Learning Frameworks for Real-Time Attitude Estimation Using 6DoF Inertial Measurement Unitscited by 4
  37. 2023Continuous Pose for Monocular Cameras in Neural Implicit Representationcited by 4
  38. 2024Light-SLAM: A Robust Deep-Learning Visual SLAM System Based on LightGlue under Challenging Lighting Conditionscited by 4

50 most cited of 95 All 95 (JSON)