mlsanityData to 7 Oct 2026

Self-Supervised Monocular Depth Estimation with Internal Feature Fusion

arXiv 2110.09482 ↗First posted 18 Oct 2021cs.CVcited by 67

Not on the map. Why?

Abstract (arXiv)

Self-supervised learning for depth estimation uses geometry in image sequences for supervision and shows promising results. Like many computer vision tasks, depth network performance is determined by the capability to learn accurate spatial and semantic representations from images. Therefore, it is natural to exploit semantic segmentation networks for depth estimation. In this work, based on a well-developed semantic segmentation network HRNet, we propose a novel depth estimation network DIFFNet, which can make use of semantic information in down and upsampling procedures. By applying feature fusion and an attention mechanism, our proposed method outperforms the state-of-the-art monocular depth estimation methods on the KITTI benchmark. Our method also demonstrates greater potential on higher resolution training data. We propose an additional extended evaluation strategy by establishing a test set of challenging cases, empirically derived from the standard benchmark.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). Builds on 30 of its 40 references that are in the map. First posted on arXiv 18 Oct 2021.

Builds on

30 of 40 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  8. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  9. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  10. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  11. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  12. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
18 more
  1. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  2. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  3. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  4. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  5. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  6. 2020Feature-metric Loss for Self-supervised Learning of Depth and Egomotioncited by 140
  7. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  8. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  9. 2020HR-Depth: High Resolution Self-Supervised Monocular Depth Estimationcited by 115
  10. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  11. 2020Unsupervised Monocular Depth Learning in Dynamic Scenescited by 84
  12. 2020The Edge of Depth: Explicit Constraints between Segmentation and Depthcited by 72
  13. 2020Forget About the LiDAR: Self-Supervised Depth Estimators with MED Probability Volumescited by 50
  14. 2019Learning Single Camera Depth Estimation using Dual-Pixelscited by 49
  15. 2020SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Drivingcited by 48
  16. 2021S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representationcited by 23
  17. 2020Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cuescited by 19
  18. 2019Inferring Distributions Over Depth from a Single Imagecited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 12; 2023: 20; 2024: 21; 2025: 6; 2026: 7.

67 papers.

Sort:

By area:

  1. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  2. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  3. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 92
  4. 2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptionscited by 47
  5. 2022RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimationcited by 36
  6. 2023Self-supervised Monocular Depth Estimation: Let's Talk About The Weathercited by 33
  7. 2023S4C: Self-Supervised Semantic Scene Completion with Neural Fieldscited by 27
  8. 2022Gradient-based Uncertainty for Monocular Depth Estimationcited by 26
  9. 2022MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and taskscited by 24
  10. 2023Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTVcited by 21
  11. 2023SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimationcited by 21
  12. 2022Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Mattercited by 18
38 more
  1. 2023DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibriumcited by 16
  2. 2023Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Networkcited by 14
  3. 2022The Monocular Depth Estimation Challengecited by 13
  4. 2023The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimationcited by 13
  5. 2023GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenescited by 13
  6. 2024Unified Domain Generalization and Adaptation for Multi-View 3D Object Detectioncited by 13
  7. 2023The Second Monocular Depth Estimation Challengecited by 12
  8. 2024Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoningcited by 12
  9. 2024DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimationcited by 12
  10. 2022SfM-TTR: Using Structure from Motion for Test-Time Refinement of Single-View Depth Networkscited by 10
  11. 2023Self-Supervised Monocular Depth Estimation with Self-Reference Distillation and Disparity Offset Refinementcited by 10
  12. 2024MonoPCC: Photometric-invariant Cycle Constraint for Monocular Depth Estimation of Endoscopic Imagescited by 10
  13. 2024The Third Monocular Depth Estimation Challengecited by 10
  14. 2024Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimationcited by 9
  15. 2024SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimationcited by 8
  16. 2025The Fourth Monocular Depth Estimation Challengecited by 8
  17. 2021SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimationcited by 7
  18. 2024Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTVcited by 7
  19. 2024SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learningcited by 7
  20. 2022Self-Supervised Monocular Depth Underwatercited by 6
  21. 2024Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillationcited by 6
  22. 2025Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimationcited by 6
  23. 2023Image Patch-Matching with Graph-Based Learning in Street Scenescited by 5
  24. 2025Revisiting Gradient-based Uncertainty for Monocular Depth Estimationcited by 5
  25. 2023A Study on the Generality of Neural Network Structures for Monocular Depth Estimationcited by 4
  26. 2023EMR-MSF: Self-Supervised Recurrent Monocular Scene Flow Exploiting Ego-Motion Rigiditycited by 4
  27. 2023Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimationcited by 4
  28. 2023EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenescited by 4
  29. 2024MambaDepth: Enhancing Long-range Dependency for Self-Supervised Fine-Structured Monocular Depth Estimationcited by 4
  30. 2024WaterMono: Teacher-Guided Anomaly Masking and Enhancement Boosting for Robust Underwater Self-Supervised Monocular Depth Estimationcited by 4
  31. 2024Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Trainingcited by 4
  32. 2023Camera Height Doesn't Change: Unsupervised Training for Metric Monocular Road-Scene Depth Estimationcited by 3
  33. 2024Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimationcited by 3
  34. 2025DMS:Diffusion-Based Multi-Baseline Stereo Generation for Improving Self-Supervised Depth Estimationcited by 3
  35. 2022On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimationcited by 2
  36. 2023Multi-Frame Self-Supervised Depth Estimation with Multi-Scale Feature Fusion in Dynamic Scenescited by 2
  37. 2023GenDepth: Generalizing Monocular Depth Estimation for Arbitrary Camera Parameters via Ground Plane Embeddingcited by 2
  38. 2024BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth Estimationcited by 2

50 most cited of 67 All 67 (JSON)