mlsanityData to 7 Oct 2026

The Second Monocular Depth Estimation Challenge

arXiv 2304.07051 ↗First posted 14 Apr 2023cs.CV cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

This paper discusses the results for the second edition of the Monocular Depth Estimation Challenge (MDEC). This edition was open to methods using any form of supervision, including fully-supervised, self-supervised, multi-task or proxy depth. The challenge was based around the SYNS-Patches dataset, which features a wide diversity of environments with high-quality dense ground-truth. This includes complex natural environments, e.g. forests or fields, which are greatly underrepresented in current benchmarks. The challenge received eight unique submissions that outperformed the provided SotA baseline on any of the pointcloud- or image-based metrics. The top supervised submission improved relative F-Score by 27.62%, while the top self-supervised improved it by 16.61%. Supervised submissions generally leveraged large collections of datasets to improve data diversity. Self-supervised submissions instead updated the network architecture and pretrained backbones. These results represent a significant progress in the field, while highlighting avenues for future research, such as reducing interpolation artifacts at depth boundaries, improving self-supervised indoor performance and overall natural image accuracy.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 87 of its 112 references that are in the map. First posted on arXiv 14 Apr 2023.

Builds on

87 of 112 references.

References · 87

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2022A ConvNet for the 2020scited by 3,545
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  7. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  9. 2021Vision Transformers for Dense Predictioncited by 1,789
  10. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  11. 2017Deformable Convolutional Networkscited by 1,481
  12. 2015Spatial Transformer Networkscited by 1,423
38 more
  1. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  2. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  3. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  4. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  6. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  7. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  8. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  9. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  10. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  11. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  12. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  13. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 593
  14. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  15. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  16. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  17. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 442
  18. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  19. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  20. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  21. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 348
  22. 2020Virtual KITTI 2cited by 345
  23. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  24. 2017Sparsity Invariant CNNscited by 325
  25. 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 297
  26. 2020One Thousand and One Hours: Self-driving Motion Prediction Datasetcited by 239
  27. 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 236
  28. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  29. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 214
  30. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  31. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 200
  32. 2018The ApolloScape Open Dataset for Autonomous Driving and its Applicationcited by 188
  33. 2021PandaSet: Advanced Sensor Suite Dataset for Autonomous Drivingcited by 186
  34. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  35. 2016Single-Image Depth Perception in the Wildcited by 179
  36. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  37. 2017Playing for Benchmarkscited by 169
  38. 2018Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstructioncited by 159

50 most cited of 87 All 87 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 5; 2025: 4.

12 papers.

  1. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  2. 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditionscited by 29
  3. 2023Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTVcited by 21
  4. 2024PatchRefiner: Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimationcited by 15
  5. 2023The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimationcited by 13
  6. 2024The Third Monocular Depth Estimation Challengecited by 10
  7. 2025The Fourth Monocular Depth Estimation Challengecited by 8
  8. 2024Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTVcited by 7
  9. 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
  10. 2025ASVSim (AirSim for Surface Vehicles): A High-Fidelity Simulation Framework for Autonomous Surface Vehicle Researchcited by 2
  11. 2024Improving classification of road surface conditions via road area extraction and contrastive learningcited by 1
  12. 2025ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Drivingcited by 1