mlsanityData to 7 Oct 2026

Adaptive Depth-converted-Scale Convolution for Self-supervised Monocular Depth Estimation

arXiv 2604.07665 ↗First posted 9 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Self-supervised monocular depth estimation (MDE) has received increasing interests in the last few years. The objects in the scene, including the object size and relationship among different objects, are the main clues to extract the scene structure. However, previous works lack the explicit handling of the changing sizes of the object due to the change of its depth. Especially in a monocular video, the size of the same object is continuously changed, resulting in size and depth ambiguity. To address this problem, we propose a Depth-converted-Scale Convolution (DcSConv) enhanced monocular depth estimation framework, by incorporating the prior relationship between the object depth and object scale to extract features from appropriate scales of the convolution receptive field. The proposed DcSConv focuses on the adaptive scale of the convolution filter instead of the local deformation of its shape. It establishes that the scale of the convolution filter matters no less (or even more in the evaluated task) than its local deformation. Moreover, a Depth-converted-Scale aware Fusion (DcS-F) is developed to adaptively fuse the DcSConv features and the conventional convolution features. Our DcSConv enhanced monocular depth estimation framework can be applied on top of existing CNN based methods as a plug-and-play module to enhance the conventional convolution block. Extensive experiments with different baselines have been conducted on the KITTI benchmark and our method achieves the best results with an improvement up to 11.6% in terms of SqRel reduction. Ablation study also validates the effectiveness of each proposed module.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 41 of its 64 references that are in the map. First posted on arXiv 9 Apr 2026.

Builds on

41 of 64 references.

References · 41

  1. 2017Squeeze-and-Excitation Networkscited by 4,763
  2. 2016Pyramid Scene Parsing Networkcited by 2,472
  3. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  4. 2021Vision Transformers for Dense Predictioncited by 1,789
  5. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  6. 2017Deformable Convolutional Networkscited by 1,481
  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. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  10. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  11. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  12. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
29 more
  1. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  2. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  3. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 355
  4. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  5. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  6. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  7. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  8. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  9. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  10. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  11. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 116
  12. 2020HR-Depth: High Resolution Self-Supervised Monocular Depth Estimationcited by 115
  13. 2022P3Depth: Monocular Depth Estimation with a Piecewise Planarity Priorcited by 106
  14. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  15. 2020Don't Forget The Past: Recurrent Depth Estimation from Monocular Videocited by 71
  16. 2023iDisc: Internal Discretization for Monocular Depth Estimationcited by 71
  17. 2019Learning monocular depth estimation infusing traditional stereo knowledgecited by 64
  18. 2021Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimationcited by 63
  19. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  20. 2021Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimationcited by 55
  21. 2021Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimationcited by 48
  22. 2021MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentscited by 38
  23. 2019Unsupervised High-Resolution Depth Learning From Videos With Dual Networkscited by 26
  24. 2020Adaptive confidence thresholding for monocular depth estimationcited by 25
  25. 2023RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenescited by 22
  26. 2018Monocular Depth Estimation with Augmented Ordinal Depth Relationshipscited by 14
  27. 2023From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Priorcited by 13
  28. 2024Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth Estimationcited by 4
  29. 2026LiftFormer: Lifting and Frame Theory Based Monocular Depth Estimation Using Depth and Edge Oriented Subspace Representationcited by 2

Built on by

Not cited yet.