mlsanityData to 14 Oct 2026

Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem

arXiv 2210.00411 ↗First posted 2 Oct 2022cs.CV cs.AI cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

Self-supervised monocular depth estimation (MDE) models universally suffer from the notorious edge-fattening issue. Triplet loss, as a widespread metric learning strategy, has largely succeeded in many computer vision applications. In this paper, we redesign the patch-based triplet loss in MDE to alleviate the ubiquitous edge-fattening issue. We show two drawbacks of the raw triplet loss in MDE and demonstrate our problem-driven redesigns. First, we present a min. operator based strategy applied to all negative samples, to prevent well-performing negatives sheltering the error of edge-fattening negatives. Second, we split the anchor-positive distance and anchor-negative distance from within the original triplet, which directly optimizes the positives without any mutual effect with the negatives. Extensive experiments show the combination of these two small redesigns can achieve unprecedented results: Our powerful and versatile triplet loss not only makes our model outperform all previous SoTA by a large margin, but also provides substantial performance boosts to a large number of existing models, while introducing no extra inference computation at all.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 42 of its 54 references that are in the map. First posted on arXiv 2 Oct 2022.

Builds on

42 of 54 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  3. 2017Deformable Convolutional Networkscited by 1,488
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  5. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  6. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 786
  7. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  8. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
  9. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
  10. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  11. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  12. 2020Consistent Video Depth Estimationcited by 220
30 more
  1. 2018PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognitioncited by 198
  2. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  3. 2014Learning Fine-grained Image Similarity with Deep Rankingcited by 190
  4. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  5. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  6. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  7. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  8. 2018Improving Semantic Segmentation via Video Propagation and Label Relaxationcited by 134
  9. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  10. 2019Self-Supervised Monocular Depth Hintscited by 127
  11. 2017Dataset Augmentation in Feature Spacecited by 124
  12. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  13. 2020HR-Depth: High Resolution Self-Supervised Monocular Depth Estimationcited by 115
  14. 2018Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understandingcited by 101
  15. 2020Unsupervised Monocular Depth Learning in Dynamic Scenescited by 84
  16. 2020The Edge of Depth: Explicit Constraints between Segmentation and Depthcited by 72
  17. 2020Don't Forget The Past: Recurrent Depth Estimation from Monocular Videocited by 71
  18. 2018SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimationcited by 64
  19. 2019Learning monocular depth estimation infusing traditional stereo knowledgecited by 64
  20. 2021Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimationcited by 63
  21. 2021Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimationcited by 55
  22. 2020Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumescited by 50
  23. 2019Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimationcited by 49
  24. 2021MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentscited by 38
  25. 2020Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptationcited by 35
  26. 2021Single Image Depth Prediction with Wavelet Decompositioncited by 34
  27. 2020Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cuescited by 19
  28. 2019Video Object Segmentation-based Visual Servo Control and Object Depth Estimation on a Mobile Robotcited by 14
  29. 2016Fast Training of Triplet-based Deep Binary Embedding Networkscited by 6
  30. 2020PLG-IN: Pluggable Geometric Consistency Loss with Wasserstein Distance in Monocular Depth Estimationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 10; 2025: 4; 2026: 2.

20 papers.

Sort:

By area:

  1. 2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptionscited by 49
  2. 2022PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planescited by 32
  3. 2025Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimationcited by 21
  4. 2023The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimationcited by 13
  5. 2024DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimationcited by 13
  6. 2022Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimationcited by 8
  7. 2024ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Predictioncited by 8
  8. 2024SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learningcited by 7
  9. 2024Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Trainingcited by 5
  10. 2024These Maps Are Made by Propagation: Adapting Deep Stereo Networks to Road Scenarios with Decisive Disparity Diffusioncited by 5
  11. 2024MonoPP: Metric-Scaled Self-Supervised Monocular Depth Estimation by Planar-Parallax Geometry in Automotive Applicationscited by 4
  12. 2024Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimationcited by 3
8 more
  1. 2024FlowDepth: Decoupling Optical Flow for Self-Supervised Monocular Depth Estimationcited by 2
  2. 2024MetricDepth: Enhancing Monocular Depth Estimation with Deep Metric Learningcited by 1
  3. 2025Towards Sharper Object Boundaries in Self-Supervised Depth Estimationcited by 1
  4. 2024Enhanced Object Tracking by Self-Supervised Auxiliary Depth Estimation Learningcited by 0
  5. 2025Bridging Geometric and Semantic Foundation Models for Generalized Monocular Depth Estimationcited by 0
  6. 2025UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometrycited by 0
  7. 2026Self-Supervised Dual-Frequency Phase Decomposition for Single-Shot Composite Fringe Projection Profilometrycited by 0
  8. 2026RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmarkcited by 0