mlsanityData to 7 Oct 2026

Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation

arXiv 2203.09737 ↗First posted 18 Mar 2022cs.CV cs.ROcited by 10

Not on the map. Why?

Abstract (arXiv)

We propose a semi-supervised learning framework for monocular depth estimation. Compared to existing semi-supervised learning methods, which inherit limitations of both sparse supervised and unsupervised loss functions, we achieve the complementary advantages of both loss functions, by building two separate network branches for each loss and distilling each other through the mutual distillation loss function. We also present to apply different data augmentation to each branch, which improves the robustness. We conduct experiments to demonstrate the effectiveness of our framework over the latest methods and provide extensive ablation studies.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 41 of its 61 references that are in the map. First posted on arXiv 18 Mar 2022.

Builds on

41 of 61 references.

References · 41

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  4. 2015Spatial Transformer Networkscited by 1,423
  5. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  7. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  8. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  9. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  10. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  11. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  12. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 507
29 more
  1. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  2. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  3. 2020Meta Pseudo Labelscited by 372
  4. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  5. 2020Rethinking Pre-training and Self-trainingcited by 352
  6. 2017Sparsity Invariant CNNscited by 325
  7. 2019Billion-scale semi-supervised learning for image classificationcited by 232
  8. 2017Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detectioncited by 209
  9. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 200
  10. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  11. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  12. 2017CNN-SLAM: Real-time dense monocular SLAM with learned depth predictioncited by 152
  13. 2019Self-Supervised Monocular Depth Hintscited by 127
  14. 2017Semi-Supervised Deep Learning for Monocular Depth Map Predictioncited by 109
  15. 2016Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networkscited by 72
  16. 2018Learning Monocular Depth by Distilling Cross-domain Stereo Networkscited by 64
  17. 2019Learning monocular depth estimation infusing traditional stereo knowledgecited by 64
  18. 2014Designing Deep Networks for Surface Normal Estimationcited by 59
  19. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  20. 2019Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimationcited by 48
  21. 2018Unsupervised Adversarial Depth Estimation using Cycled Generative Networkscited by 45
  22. 2020Learning Stereo from Single Imagescited by 44
  23. 2015Loss Functions for Neural Networks for Image Processingcited by 41
  24. 2018Single View Stereo Matchingcited by 39
  25. 2019Unsupervised Domain Adaptation for Depth Prediction from Imagescited by 29
  26. 2020Adaptive confidence thresholding for monocular depth estimationcited by 25
  27. 2019Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Networkcited by 21
  28. 2016Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fieldscited by 17
  29. 2019Self-supervised blur detection from synthetically blurred scenescited by 3

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 3; 2024: 1; 2025: 1.

10 papers.

  1. 2022UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robotscited by 27
  2. 2024PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentationcited by 21
  3. 2022Bidirectional Semi-supervised Dual-branch CNN for Robust 3D Reconstruction of Stereo Endoscopic Images via Adaptive Cross and Parallel Supervisionscited by 6
  4. 2022Outdoor Monocular Depth Estimation: A Research Reviewcited by 4
  5. 2022Composite Learning for Robust and Effective Dense Predictionscited by 4
  6. 2023ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimationcited by 2
  7. 2023Do More With What You Have: Transferring Depth-Scale from Labeled to Unlabeled Domainscited by 1
  8. 2025Endoscopic Depth Estimation Based on Deep Learning: A Surveycited by 1
  9. 2022MaskingDepth: Masked Consistency Regularization for Semi-supervised Monocular Depth Estimationcited by 0
  10. 2023Exploring the Mutual Influence between Self-Supervised Single-Frame and Multi-Frame Depth Estimationcited by 0