mlsanityData to 7 Oct 2026

Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion

arXiv 2304.08916 ↗First posted 18 Apr 2023cs.CV cs.LG cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Self-supervised monocular depth estimation approaches suffer not only from scale ambiguity but also infer temporally inconsistent depth maps w.r.t. scale. While disambiguating scale during training is not possible without some kind of ground truth supervision, having scale consistent depth predictions would make it possible to calculate scale once during inference as a post-processing step and use it over-time. With this as a goal, a set of temporal consistency losses that minimize pose inconsistencies over time are introduced. Evaluations show that introducing these constraints not only reduces depth inconsistencies but also improves the baseline performance of depth and ego-motion prediction.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 61 references that are in the map. First posted on arXiv 18 Apr 2023.

Builds on

40 of 61 references.

References · 40

  1. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  2. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  3. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  4. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  6. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  7. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  8. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  9. 2017Sparsity Invariant CNNscited by 325
  10. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  11. 2020Consistent Video Depth Estimationcited by 220
  12. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
28 more
  1. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  2. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  3. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  4. 2019Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Cameracited by 130
  5. 2017Semi-Supervised Deep Learning for Monocular Depth Map Predictioncited by 109
  6. 2017Coherent Online Video Style Transfercited by 96
  7. 2017UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learningcited by 95
  8. 2020Towards Better Generalization: Joint Depth-Pose Learning without PoseNetcited by 85
  9. 2020Unsupervised Monocular Depth Learning in Dynamic Scenescited by 84
  10. 2020Don't Forget The Past: Recurrent Depth Estimation from Monocular Videocited by 71
  11. 2020World-Consistent Video-to-Video Synthesiscited by 69
  12. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  13. 2019Exploiting temporal consistency for real-time video depth estimationcited by 61
  14. 2019DepthTransfer: Depth Extraction from Video Using Non-parametric Samplingcited by 60
  15. 2019Visual Odometry Revisited: What Should Be Learnt?cited by 57
  16. 2019Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depthcited by 50
  17. 2020Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Predictioncited by 41
  18. 2020Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applicationscited by 40
  19. 2020Learning Monocular Visual Odometry via Self-Supervised Long-Term Modelingcited by 39
  20. 2022Learning Optical Flow, Depth, and Scene Flow without Real-World Labelscited by 31
  21. 2021Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimationcited by 27
  22. 2020Self-Supervised Scale Recovery for Monocular Depth and Egomotion Estimationcited by 21
  23. 2021Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimationcited by 16
  24. 2021Perceptual Consistency in Video Segmentationcited by 12
  25. 2018Geometric Consistency for Self-Supervised End-to-End Visual Odometrycited by 11
  26. 2022Visual Attention-based Self-supervised Absolute Depth Estimation using Geometric Priors in Autonomous Drivingcited by 8
  27. 2020Calibrating Self-supervised Monocular Depth Estimationcited by 7
  28. 2018Sparse-to-Continuous: Enhancing Monocular Depth Estimation using Occupancy Mapscited by 3

Built on by

Not cited yet.