mlsanityData to 7 Oct 2026

Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimation

arXiv 2210.03952 ↗First posted 8 Oct 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Monocular depth estimation (MDE) in the self-supervised scenario has emerged as a promising method as it refrains from the requirement of ground truth depth. Despite continuous efforts, MDE is still sensitive to scale changes especially when all the training samples are from one single camera. Meanwhile, it deteriorates further since camera movement results in heavy coupling between the predicted depth and the scale change. In this paper, we present a scale-invariant approach for self-supervised MDE, in which scale-sensitive features (SSFs) are detached away while scale-invariant features (SIFs) are boosted further. To be specific, a simple but effective data augmentation by imitating the camera zooming process is proposed to detach SSFs, making the model robust to scale changes. Besides, a dynamic cross-attention module is designed to boost SIFs by fusing multi-scale cross-attention features adaptively. Extensive experiments on the KITTI dataset demonstrate that the detaching and boosting strategies are mutually complementary in MDE and our approach achieves new State-of-The-Art performance against existing works from 0.097 to 0.090 w.r.t absolute relative error. The code will be made public soon.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 38 references that are in the map. First posted on arXiv 8 Oct 2022.

Builds on

33 of 38 references.

References · 33

  1. 2017Non-local Neural Networkscited by 2,290
  2. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  3. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  4. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  6. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  7. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  8. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  9. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  10. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  11. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 355
  12. 2020Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformerscited by 190
21 more
  1. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  2. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  3. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  4. 2020Feature-metric Loss for Self-supervised Learning of Depth and Egomotioncited by 140
  5. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  6. 2019Self-Supervised Monocular Depth Hintscited by 127
  7. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  8. 2020HR-Depth: High Resolution Self-Supervised Monocular Depth Estimationcited by 115
  9. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  10. 2018Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometrycited by 85
  11. 2020The Edge of Depth: Explicit Constraints between Segmentation and Depthcited by 72
  12. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  13. 2021Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimationcited by 63
  14. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  15. 2021Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimationcited by 55
  16. 2020Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumescited by 50
  17. 2021Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimationcited by 48
  18. 2018Single View Stereo Matchingcited by 39
  19. 2021MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentscited by 38
  20. 2021PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Losscited by 31
  21. 2020Monocular Depth Estimation Using Multi Scale Neural Network And Feature Fusioncited by 7

Built on by

Not cited yet.