mlsanityData to 7 Oct 2026

SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation

arXiv 2111.09692 ↗First posted 18 Nov 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We propose SUB-Depth, a universal multi-task training framework for self-supervised monocular depth estimation (SDE). Depth models trained with SUB-Depth outperform the same models trained in a standard single-task SDE framework. By introducing an additional self-distillation task into a standard SDE training framework, SUB-Depth trains a depth network, not only to predict the depth map for an image reconstruction task, but also to distill knowledge from a trained teacher network with unlabelled data. To take advantage of this multi-task setting, we propose homoscedastic uncertainty formulations for each task to penalize areas likely to be affected by teacher network noise, or violate SDE assumptions. We present extensive evaluations on KITTI to demonstrate the improvements achieved by training a range of existing networks using the proposed framework, and we achieve state-of-the-art performance on this task. Additionally, SUB-Depth enables models to estimate uncertainty on depth output.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 39 of its 51 references that are in the map. First posted on arXiv 18 Nov 2021.

Builds on

39 of 51 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  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. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  7. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  8. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  9. 2020Gradient Surgery for Multi-Task Learningcited by 1,210
  10. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  11. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
  12. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
27 more
  1. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  2. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  3. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
  4. 2017Sparsity Invariant CNNscited by 325
  5. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  6. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  7. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  8. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  9. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  10. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  11. 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
  12. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  13. 2020HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matchingcited by 120
  14. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  15. 2020HR-Depth: High Resolution Self-Supervised Monocular Depth Estimationcited by 115
  16. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  17. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  18. 2019Learning Single Camera Depth Estimation using Dual-Pixelscited by 49
  19. 2020SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Drivingcited by 48
  20. 2020Bidirectional Attention Network for Monocular Depth Estimationcited by 48
  21. 2018ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systemscited by 35
  22. 2020UnRectDepthNet: Self-Supervised Monocular Depth Estimation using a Generic Framework for Handling Common Camera Distortion Modelscited by 33
  23. 2021SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular imagescited by 33
  24. 2021S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representationcited by 23
  25. 2019MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classificationcited by 13
  26. 2021X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillationcited by 12
  27. 2021CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameterscited by 8

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4; 2024: 0; 2025: 1.

7 papers.

  1. 2022Gradient-based Uncertainty for Monocular Depth Estimationcited by 26
  2. 2023EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenescited by 4
  3. 2022Uncertainty Guided Depth Fusion for Spike Cameracited by 2
  4. 2023ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimationcited by 2
  5. 2023Measuring and Modeling Uncertainty Degree for Monocular Depth Estimationcited by 1
  6. 2023Exploring the Mutual Influence between Self-Supervised Single-Frame and Multi-Frame Depth Estimationcited by 0
  7. 2025Bridging Geometric and Semantic Foundation Models for Generalized Monocular Depth Estimationcited by 0