mlsanityData to 7 Oct 2026

UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler

arXiv 2502.20110 ↗First posted 27 Feb 2025cs.CVcited by 170

Not on the map. Why?

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, UniDepthV2, capable of reconstructing metric 3D scenes from solely single images across domains. Departing from the existing MMDE paradigm, UniDepthV2 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, UniDepthV2 implements a self-promptable camera module predicting a dense camera representation to condition depth features. Our model exploits a pseudo-spherical output representation, which disentangles the camera and depth representations. In addition, we propose a geometric invariance loss that promotes the invariance of camera-prompted depth features. UniDepthV2 improves its predecessor UniDepth model via a new edge-guided loss which enhances the localization and sharpness of edges in the metric depth outputs, a revisited, simplified and more efficient architectural design, and an additional uncertainty-level output which enables downstream tasks requiring confidence. Thorough evaluations on ten depth datasets in a zero-shot regime consistently demonstrate the superior performance and generalization of UniDepthV2. Code and models are available at https://github.com/lpiccinelli-eth/UniDepth

Key facts. Cited by 170 papers in the map (data through 7 Oct 2026). Builds on 73 of its 95 references that are in the map. First posted on arXiv 27 Feb 2025.

Builds on

73 of 95 references.

References · 73

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2023Segment Anythingcited by 8,158
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  7. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  8. 2021Vision Transformers for Dense Predictioncited by 1,789
  9. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  10. 2024Depth Anything V2cited by 1,385
  11. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  12. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
38 more
  1. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  2. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  3. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  4. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  5. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  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. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 579
  12. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
  13. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  14. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  15. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  16. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 442
  17. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  18. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  19. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  20. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  21. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  22. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  23. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  24. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  25. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 323
  26. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 321
  27. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
  28. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 274
  29. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  30. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  31. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 214
  32. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 202
  33. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 202
  34. 2020A2D2: Audi Autonomous Driving Datasetcited by 189
  35. 2023MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyondcited by 185
  36. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  37. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  38. 2024Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Predictioncited by 163

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 58; 2026: 112.

170 papers.

Sort:

By area:

  1. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  2. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  3. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 250
  4. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 162
  5. 2025SpatialVID: A Large-Scale Video Dataset with Spatial Annotationscited by 72
  6. 2025UniK3D: Universal Camera Monocular 3D Estimationcited by 60
  7. 20254DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videoscited by 46
  8. 2025Efficiently Reconstructing Dynamic Scenes One D4RT at a Timecited by 46
  9. 2025DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoningcited by 44
  10. 2026Image Generators are Generalist Vision Learnerscited by 40
  11. 2025MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Secondcited by 31
  12. 2025DepthLM: Metric Depth From Vision Language Modelscited by 29
38 more
  1. 2025SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Drivingcited by 28
  2. 2025Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Videocited by 27
  3. 2026VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Controlcited by 26
  4. 2025Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimationcited by 24
  5. 2025Back on Track: Bundle Adjustment for Dynamic Scene Reconstructioncited by 23
  6. 2025Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matchingcited by 23
  7. 2025DA2: Depth Anything in Any Directioncited by 22
  8. 2026DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Drivingcited by 20
  9. 2025Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenescited by 19
  10. 2025MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusioncited by 18
  11. 2025SpaceVista: All-Scale Visual Spatial Reasoning from mm to kmcited by 18
  12. 2026DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planningcited by 17
  13. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 16
  14. 2025BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignmentcited by 15
  15. 2026Vista4D: Video Reshooting with 4D Point Cloudscited by 15
  16. 2025CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interactioncited by 14
  17. 2025HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Videocited by 13
  18. 2026Any3D-VLA: Enhancing VLA Robustness via Diverse Point Cloudscited by 13
  19. 2026Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D Worldcited by 11
  20. 20253D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detectioncited by 10
  21. 2026MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sourcescited by 10
  22. 2025MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generationcited by 9
  23. 2025Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokenscited by 9
  24. 2026SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generationcited by 9
  25. 2025Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimationcited by 8
  26. 2025The Fourth Monocular Depth Estimation Challengecited by 8
  27. 2026WHOLE: World-Grounded Hand-Object Lifted from Egocentric Videoscited by 7
  28. 2026On the Generalization Capacities of MLLMs for Spatial Intelligencecited by 7
  29. 2026UniDAC: Universal Metric Depth Estimation for Any Cameracited by 7
  30. 2026SceneTok: A Compressed, Diffusable Token Space for 3D Scenescited by 6
  31. 2025Radar-Guided Polynomial Fitting for Metric Depth Estimationcited by 5
  32. 2025DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modelingcited by 5
  33. 2026TruckDrive: Long-Range Autonomous Highway Driving Datasetcited by 5
  34. 2026Any to Full: Prompting Depth Anything for Depth Completion in One Stagecited by 5
  35. 2026PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimationcited by 5
  36. 2025CARE: Enhancing Safety of Visual Navigation through Collision Avoidance via Repulsive Estimationcited by 4
  37. 2025Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbationscited by 4
  38. 2025DGFusion: Depth-Guided Sensor Fusion for Robust Semantic Perceptioncited by 4

50 most cited of 170 All 170 (JSON)