mlsanityData to 14 Oct 2026

Self-Supervised Monocular Depth Estimation with Self-Reference Distillation and Disparity Offset Refinement

arXiv 2302.09789 ↗First posted 20 Feb 2023cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Monocular depth estimation plays a fundamental role in computer vision. Due to the costly acquisition of depth ground truth, self-supervised methods that leverage adjacent frames to establish a supervisory signal have emerged as the most promising paradigms. In this work, we propose two novel ideas to improve self-supervised monocular depth estimation: 1) self-reference distillation and 2) disparity offset refinement. Specifically, we use a parameter-optimized model as the teacher updated as the training epochs to provide additional supervision during the training process. The teacher model has the same structure as the student model, with weights inherited from the historical student model. In addition, a multiview check is introduced to filter out the outliers produced by the teacher model. Furthermore, we leverage the contextual consistency between high-scale and low-scale features to obtain multiscale disparity offsets, which are used to refine the disparity output incrementally by aligning disparity information at different scales. The experimental results on the KITTI and Make3D datasets show that our method outperforms previous state-of-the-art competitors.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 51 of its 77 references that are in the map. First posted on arXiv 20 Feb 2023.

Builds on

51 of 77 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  6. 2021Vision Transformers for Dense Predictioncited by 1,803
  7. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  8. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  9. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  10. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  11. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  12. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
38 more
  1. 2018Born Again Neural Networkscited by 546
  2. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
  3. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  4. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 382
  5. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  6. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  7. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  8. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  9. 2015Cross Modal Distillation for Supervision Transfercited by 175
  10. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  11. 2017Learning from Noisy Labels with Distillationcited by 161
  12. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  13. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  14. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  15. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  16. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  17. 2020Semantic Flow for Fast and Accurate Scene Parsingcited by 128
  18. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  19. 2021MPViT: Multi-Path Vision Transformer for Dense Predictioncited by 122
  20. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  21. 2020HR-Depth: High Resolution Self-Supervised Monocular Depth Estimationcited by 115
  22. 2017Semi-Supervised Deep Learning for Monocular Depth Map Predictioncited by 109
  23. 2018Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometrycited by 85
  24. 2021FaPN: Feature-aligned Pyramid Network for Dense Image Predictioncited by 81
  25. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  26. 2018Learning Monocular Depth by Distilling Cross-domain Stereo Networkscited by 64
  27. 2021Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimationcited by 63
  28. 2020DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learningcited by 60
  29. 2018AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimationcited by 54
  30. 2020AlignSeg: Feature-Aligned Segmentation Networkscited by 53
  31. 2018LEGO: Learning Edge with Geometry all at Once by Watching Videoscited by 47
  32. 2021Self-supervised Monocular Depth Estimation for All Day Images using Domain Separationcited by 44
  33. 2017Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistencycited by 40
  34. 2018Single View Stereo Matchingcited by 39
  35. 2021Single Image Depth Prediction with Wavelet Decompositioncited by 34
  36. 2021Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervisioncited by 24
  37. 2021GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Networkcited by 12
  38. 2021Shallow Features Guide Unsupervised Domain Adaptation for Semantic Segmentation at Class Boundariescited by 10

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 6; 2025: 1.

10 papers.

  1. 2023MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Modelcited by 13
  2. 2024Diffusion-Based Depth Inpainting for Transparent and Reflective Objectscited by 9
  3. 2024FisheyeDepth: A Real Scale Self-Supervised Depth Estimation Model for Fisheye Cameracited by 8
  4. 2023EndoDepthL: Lightweight Endoscopic Monocular Depth Estimation with CNN-Transformercited by 2
  5. 2023ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimationcited by 2
  6. 2025RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditionscited by 2
  7. 2024Self-supervised Pretraining and Finetuning for Monocular Depth and Visual Odometrycited by 1
  8. 2024MetricDepth: Enhancing Monocular Depth Estimation with Deep Metric Learningcited by 1
  9. 2024DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videoscited by 0
  10. 2024FA-Depth: Toward Fast and Accurate Self-supervised Monocular Depth Estimationcited by 0