The Third Monocular Depth Estimation Challenge
Not on the map. Why?
Abstract (arXiv)
This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC). The challenge focuses on zero-shot generalization to the challenging SYNS-Patches dataset, featuring complex scenes in natural and indoor settings. As with the previous edition, methods can use any form of supervision, i.e. supervised or self-supervised. The challenge received a total of 19 submissions outperforming the baseline on the test set: 10 among them submitted a report describing their approach, highlighting a diffused use of foundational models such as Depth Anything at the core of their method. The challenge winners drastically improved 3D F-Score performance, from 17.51% to 23.72%.
Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 99 of its 126 references that are in the map. First posted on arXiv 25 Apr 2024.
Builds on
99 of 126 references.
References · 99
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2020Denoising Diffusion Implicit Modelscited by 9,781
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
- 2022A ConvNet for the 2020scited by 3,579
- 2021Vision Transformers for Dense Predictioncited by 1,803
- 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
- 2015Spatial Transformer Networkscited by 1,429
- 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
- 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
38 more
- 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
- 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
- 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
- 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
- 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
- 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
- 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
- 2022Simple Baselines for Image Restorationcited by 708
- 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
- 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
- 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
- 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
- 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
- 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
- 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
- 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
- 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 342
- 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
- 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 286
- 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
- 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 240
- 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
- 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
- 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
- 2018The ApolloScape Open Dataset for Autonomous Driving and its Applicationcited by 190
- 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
- 2016Single-Image Depth Perception in the Wildcited by 180
- 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
- 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
- 2018Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstructioncited by 159
- 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
- 2022NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimationcited by 153
- 2023DDP: Diffusion Model for Dense Visual Predictioncited by 148
- 2018Evaluation of CNN-based Single-Image Depth Estimation Methodscited by 138
- 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
- 2019Self-Supervised Monocular Depth Hintscited by 127
- 2021SMD-Nets: Stereo Mixture Density Networkscited by 120
- 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
50 most cited of 99 All 99 (JSON)
Built on by
Citing papers per year: 2024: 5; 2025: 4; 2026: 1.
10 papers.
- 2024Depth Anything V2cited by 1,422
- 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditionscited by 29
- 2025LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoningcited by 8
- 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
- 2024NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-trainingcited by 2
- 2024Refinement of Monocular Depth Maps via Multi-View Differentiable Renderingcited by 1
- 2024Single-Shot Metric Depth from Focused Plenoptic Camerascited by 1
- 2025ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Drivingcited by 1
- 2026ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Devicecited by 1
- 2025Survey on Monocular Metric Depth Estimationcited by 0
- 2026ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device9 Jul 2026
- 2025ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving19 Aug 2025
- 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces6 Jun 2025
- 2025LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning25 Apr 2025
- 2025Survey on Monocular Metric Depth Estimation21 Jan 2025
- 2024Single-Shot Metric Depth from Focused Plenoptic Cameras3 Dec 2024
- 2024Refinement of Monocular Depth Maps via Multi-View Differentiable Rendering4 Oct 2024
- 2024NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training26 Aug 2024
- 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions23 Jul 2024
- 2024Depth Anything V213 Jun 2024