mlsanityData to 7 Oct 2026

Deep Ordinal Regression Network for Monocular Depth Estimation

arXiv 1806.02446 ↗First posted 6 Jun 2018cs.CVcited by 721

Not on the map. Why?

Cited by 36 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Monocular depth estimation, which plays a crucial role in understanding 3D scene geometry, is an ill-posed problem. Recent methods have gained significant improvement by exploring image-level information and hierarchical features from deep convolutional neural networks (DCNNs). These methods model depth estimation as a regression problem and train the regression networks by minimizing mean squared error, which suffers from slow convergence and unsatisfactory local solutions. Besides, existing depth estimation networks employ repeated spatial pooling operations, resulting in undesirable low-resolution feature maps. To obtain high-resolution depth maps, skip-connections or multi-layer deconvolution networks are required, which complicates network training and consumes much more computations. To eliminate or at least largely reduce these problems, we introduce a spacing-increasing discretization (SID) strategy to discretize depth and recast depth network learning as an ordinal regression problem. By training the network using an ordinary regression loss, our method achieves much higher accuracy and ddfaster convergence in synch. Furthermore, we adopt a multi-scale network structure which avoids unnecessary spatial pooling and captures multi-scale information in parallel. The method described in this paper achieves state-of-the-art results on four challenging benchmarks, i.e., KITTI [17], ScanNet [9], Make3D [50], and NYU Depth v2 [42], and win the 1st prize in Robust Vision Challenge 2018. Code has been made available at: https://github.com/hufu6371/DORN.

Key facts. Cited by 721 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 146; 2022: 162; 2023: 137; 2024: 122; 2025: 90; 2026: 64.

721 papers.

Sort:

By area:

  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2024Depth Anything V2cited by 1,385
  3. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 679
  4. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  5. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  6. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  7. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  8. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  9. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 323
  10. 2021Neural RGB-D Surface Reconstructioncited by 312
  11. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  12. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 250
38 more
  1. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  2. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  3. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 202
  4. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 202
  5. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  6. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  7. 2022Depth-Aware Generative Adversarial Network for Talking Head Video Generationcited by 177
  8. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  9. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 170
  10. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 166
  11. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 165
  12. 2024Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Predictioncited by 163
  13. 2022Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wildcited by 159
  14. 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
  15. 2022NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimationcited by 151
  16. 2023DDP: Diffusion Model for Dense Visual Predictioncited by 148
  17. 2024SpatialBot: Precise Spatial Understanding with Vision Language Modelscited by 146
  18. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 138
  19. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  20. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  21. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  22. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 116
  23. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
  24. 2022MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformercited by 108
  25. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  26. 2022P3Depth: Monocular Depth Estimation with a Piecewise Planarity Priorcited by 106
  27. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  28. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  29. 2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 100
  30. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  31. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 92
  32. 2022Attention Attention Everywhere: Monocular Depth Prediction with Skip Attentioncited by 92
  33. 2021UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimationcited by 91
  34. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 89
  35. 2021Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Predictioncited by 88
  36. 2023Monocular Depth Estimation using Diffusion Modelscited by 87
  37. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 85
  38. 2021Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detectioncited by 84

50 most cited of 721 All 721 (JSON)