mlsanityData to 7 Oct 2026

SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning

arXiv 2203.05332 ↗First posted 10 Mar 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Monocular depth estimation in the wild inherently predicts depth up to an unknown scale. To resolve scale ambiguity issue, we present a learning algorithm that leverages monocular simultaneous localization and mapping (SLAM) with proprioceptive sensors. Such monocular SLAM systems can provide metrically scaled camera poses. Given these metric poses and monocular sequences, we propose a self-supervised learning method for the pre-trained supervised monocular depth networks to enable metrically scaled depth estimation. Our approach is based on a teacher-student formulation which guides our network to predict high-quality depths. We demonstrate that our approach is useful for various applications such as mobile robot navigation and is applicable to diverse environments. Our full system shows improvements over recent self-supervised depth estimation and completion methods on EuRoC, OpenLORIS, and ScanNet datasets.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 40 of its 52 references that are in the map. First posted on arXiv 10 Mar 2022.

Builds on

40 of 52 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  7. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  8. 2015Spatial Transformer Networkscited by 1,423
  9. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  10. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  11. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  12. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
28 more
  1. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  2. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  3. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  4. 2017VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimatorcited by 418
  5. 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
  6. 2020Consistent Video Depth Estimationcited by 220
  7. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 214
  8. 2019Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mappingcited by 181
  9. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
  10. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  11. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  12. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  13. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 109
  14. 2015On-Manifold Preintegration for Real-Time Visual-Inertial Odometrycited by 95
  15. 2019Unsupervised Depth Completion from Visual Inertial Odometrycited by 88
  16. 2019Web Stereo Video Supervision for Depth Prediction from Dynamic Scenescited by 73
  17. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  18. 2020Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to Endcited by 55
  19. 2020Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applicationscited by 40
  20. 2019Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAMcited by 39
  21. 2018Propagating Confidences through CNNs for Sparse Data Regressioncited by 36
  22. 2018ADVIO: An authentic dataset for visual-inertial odometrycited by 22
  23. 2020Self-Supervised Scale Recovery for Monocular Depth and Egomotion Estimationcited by 21
  24. 2021DenseLiDAR: A Real-Time Pseudo Dense Depth Guided Depth Completion Networkcited by 17
  25. 2020Deep Depth Estimation from Visual-Inertial SLAMcited by 13
  26. 2020SelfDeco: Self-Supervised Monocular Depth Completion in Challenging Indoor Environmentscited by 13
  27. 2020Volumetric Occupancy Mapping With Probabilistic Depth Completion for Robotic Navigationcited by 13
  28. 2021DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenescited by 5

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 2.

4 papers.

  1. 2023STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimationcited by 36
  2. 2023DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptationcited by 25
  3. 2025RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimizationcited by 4
  4. 2025MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistencycited by 3