mlsanityData to 7 Oct 2026

UniDepth: Universal Monocular Metric Depth Estimation

arXiv 2403.18913 ↗First posted 27 Mar 2024cs.CVcited by 375

Not on the map. Why?

Cited by 32 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Accurate monocular metric depth estimation (MMDE) is crucial to solving downstream tasks in 3D perception and modeling. However, the remarkable accuracy of recent MMDE methods is confined to their training domains. These methods fail to generalize to unseen domains even in the presence of moderate domain gaps, which hinders their practical applicability. We propose a new model, UniDepth, capable of reconstructing metric 3D scenes from solely single images across domains. Departing from the existing MMDE methods, UniDepth directly predicts metric 3D points from the input image at inference time without any additional information, striving for a universal and flexible MMDE solution. In particular, UniDepth implements a self-promptable camera module predicting dense camera representation to condition depth features. Our model exploits a pseudo-spherical output representation, which disentangles camera and depth representations. In addition, we propose a geometric invariance loss that promotes the invariance of camera-prompted depth features. Thorough evaluations on ten datasets in a zero-shot regime consistently demonstrate the superior performance of UniDepth, even when compared with methods directly trained on the testing domains. Code and models are available at: https://github.com/lpiccinelli-eth/unidepth

Key facts. Cited by 375 papers in the map (data through 7 Oct 2026). Builds on 52 of its 67 references that are in the map. First posted on arXiv 27 Mar 2024.

Builds on

52 of 67 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2016Densely Connected Convolutional Networkscited by 6,691
  7. 2016Layer Normalizationcited by 5,579
  8. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  10. 2022A ConvNet for the 2020scited by 3,545
  11. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  12. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
38 more
  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  3. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  5. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  6. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  7. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  8. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  9. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  10. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  11. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  12. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  13. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  14. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  15. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  16. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  17. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  18. 2019Adversarial Examples Improve Image Recognitioncited by 283
  19. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  20. 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 236
  21. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 214
  22. 2020A2D2: Audi Autonomous Driving Datasetcited by 189
  23. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  24. 2022NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimationcited by 151
  25. 2020Train in Germany, Test in The USA: Making 3D Object Detectors Generalizecited by 150
  26. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  27. 2022P3Depth: Monocular Depth Estimation with a Piecewise Planarity Priorcited by 106
  28. 2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 100
  29. 2019Unsupervised Depth Completion from Visual Inertial Odometrycited by 88
  30. 2019CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depthcited by 75
  31. 2023iDisc: Internal Discretization for Monocular Depth Estimationcited by 71
  32. 2019Does computer vision matter for action?cited by 64
  33. 2021Towards Real-Time Monocular Depth Estimation for Robotics: A Surveycited by 55
  34. 2023VA-DepthNet: A Variational Approach to Single Image Depth Predictioncited by 54
  35. 2023IEBins: Iterative Elastic Bins for Monocular Depth Estimationcited by 53
  36. 2023NDDepth: Normal-Distance Assisted Monocular Depth Estimationcited by 45
  37. 2022From 2D to 3D: Re-thinking Benchmarking of Monocular Depth Predictioncited by 19
  38. 2022Is my Depth Ground-Truth Good Enough? HAMMER -- Highly Accurate Multi-Modal Dataset for DEnse 3D Scene Regressioncited by 18

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 63; 2025: 175; 2026: 137.

375 papers.

Sort:

By area:

  1. 2024Depth Anything V2cited by 1,385
  2. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  3. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  4. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  5. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 290
  6. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  7. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 250
  8. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
  9. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
  10. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 202
  11. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 202
  12. 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 177
38 more
  1. 2024Motion Prompting: Controlling Video Generation with Motion Trajectoriescited by 176
  2. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 170
  3. 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Modelscited by 160
  4. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
  5. 2025CAST: Component-Aligned 3D Scene Reconstruction from an RGB Imagecited by 101
  6. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  7. 2024Stereo4D: Learning How Things Move in 3D from Internet Stereo Videoscited by 89
  8. 2025Easi3R: Estimating Disentangled Motion from DUSt3R Without Trainingcited by 88
  9. 2025St4RTrack: Simultaneous 4D Reconstruction and Tracking in the Worldcited by 88
  10. 2025Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modelingcited by 86
  11. 2025SpatialTrackerV2: 3D Point Tracking Made Easycited by 84
  12. 2024Fine-Tuning Image-Conditional Diffusion Models is Easier than You Thinkcited by 82
  13. 2024Align3R: Aligned Monocular Depth Estimation for Dynamic Videoscited by 79
  14. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 73
  15. 2025SpatialVID: A Large-Scale Video Dataset with Spatial Annotationscited by 72
  16. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 69
  17. 2025Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videoscited by 63
  18. 2024DELTA: Dense Efficient Long-range 3D Tracking for any videocited by 62
  19. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 60
  20. 2025UniK3D: Universal Camera Monocular 3D Estimationcited by 60
  21. 2025WorldMirror: Universal 3D World Reconstruction with Any-Prior Promptingcited by 60
  22. 2024MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priorscited by 51
  23. 2024Matching Anything by Segmenting Anythingcited by 49
  24. 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformerscited by 47
  25. 20254DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videoscited by 46
  26. 2025LONG3R: Long Sequence Streaming 3D Reconstructioncited by 45
  27. 2024SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Videocited by 44
  28. 2025Dens3R: A Foundation Model for 3D Geometry Predictioncited by 44
  29. 2024I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strengthcited by 38
  30. 2025Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Cameracited by 38
  31. 2025GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Trackingcited by 37
  32. 2024StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videoscited by 36
  33. 2025GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priorscited by 36
  34. 2025Detect Anything 3D in the Wildcited by 32
  35. 2024Splatter a Video: Video Gaussian Representation for Versatile Processingcited by 31
  36. 2025MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Secondcited by 31
  37. 2024Cross-View Completion Models are Zero-shot Correspondence Estimatorscited by 30
  38. 2025DepthLM: Metric Depth From Vision Language Modelscited by 29

50 most cited of 375 All 375 (JSON)