mlsanityData to 7 Oct 2026

Improving Monocular Visual Odometry Using Learned Depth

arXiv 2204.01268 ↗First posted 4 Apr 2022cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

Monocular visual odometry (VO) is an important task in robotics and computer vision. Thus far, how to build accurate and robust monocular VO systems that can work well in diverse scenarios remains largely unsolved. In this paper, we propose a framework to exploit monocular depth estimation for improving VO. The core of our framework is a monocular depth estimation module with a strong generalization capability for diverse scenes. It consists of two separate working modes to assist the localization and mapping. With a single monocular image input, the depth estimation module predicts a relative depth to help the localization module on improving the accuracy. With a sparse depth map and an RGB image input, the depth estimation module can generate accurate scale-consistent depth for dense mapping. Compared with current learning-based VO methods, our method demonstrates a stronger generalization ability to diverse scenes. More significantly, our framework is able to boost the performances of existing geometry-based VO methods by a large margin.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 42 of its 78 references that are in the map. First posted on arXiv 4 Apr 2022.

Builds on

42 of 78 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  7. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  8. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  9. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  10. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  12. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
30 more
  1. 2016Direct Sparse Odometrycited by 479
  2. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  3. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  4. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 285
  5. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  6. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  7. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 214
  8. 2016Single-Image Depth Perception in the Wildcited by 179
  9. 2017DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networkscited by 173
  10. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
  11. 2018Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstructioncited by 159
  12. 2017CNN-SLAM: Real-time dense monocular SLAM with learned depth predictioncited by 152
  13. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
  14. 2018High Quality Monocular Depth Estimation via Transfer Learningcited by 133
  15. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  16. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 109
  17. 2019Depth Completion from Sparse LiDAR Data with Depth-Normal Constraintscited by 108
  18. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  19. 2017UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learningcited by 95
  20. 2019Web Stereo Video Supervision for Depth Prediction from Dynamic Scenescited by 73
  21. 2020DiverseDepth: Affine-invariant Depth Prediction Using Diverse Datacited by 60
  22. 2020An Overview of Neural Network Compressioncited by 59
  23. 2018Confidence Propagation through CNNs for Guided Sparse Depth Regressioncited by 52
  24. 2021Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Predictioncited by 48
  25. 2017Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Camerascited by 45
  26. 2020Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Predictioncited by 41
  27. 2018Propagating Confidences through CNNs for Sparse Data Regressioncited by 36
  28. 2018Learning Single-Image Depth from Videos using Quality Assessment Networkscited by 25
  29. 2018CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Predictioncited by 17
  30. 2013A Joint Intensity and Depth Co-Sparse Analysis Model for Depth Map Super-Resolutioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 5; 2024: 5; 2025: 4; 2026: 1.

17 papers.

Sort:

  1. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  2. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  3. 2022Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Imagecited by 42
  4. 2023Deep Learning for Visual Localization and Mapping: A Surveycited by 14
  5. 2023Deep Visual Odometry with Events and Framescited by 13
  6. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 13
  7. 2025Scene-agnostic Pose Regression for Visual Localizationcited by 8
  8. 2024GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Modelscited by 5
  9. 2024DBA-Fusion: Tightly Integrating Deep Dense Visual Bundle Adjustment with Multiple Sensors for Large-Scale Localization and Mappingcited by 4
  10. 2024Light-SLAM: A Robust Deep-Learning Visual SLAM System Based on LightGlue under Challenging Lighting Conditionscited by 4
  11. 2023Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimationcited by 2
  12. 2023Depth Completion with Multiple Balanced Bases and Confidence for Dense Monocular SLAMcited by 2
5 more
  1. 2024CodedVO: Coded Visual Odometrycited by 1
  2. 2025YOWO: You Only Walk Once to Jointly Map An Indoor Scene and Register Ceiling-mounted Camerascited by 1
  3. 2022Progressive Self-Distillation for Ground-to-Aerial Perception Knowledge Transfercited by 0
  4. 2025Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learningcited by 0
  5. 2026MDE-VIO: Enhancing Visual-Inertial Odometry Using Learned Depth Priorscited by 0