mlsanityData to 7 Oct 2026

MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details

arXiv 2507.02546 ↗First posted 3 Jul 2025cs.CVcited by 250

Not on the map. Why?

Cited by 20 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose MoGe-2, an advanced open-domain geometry estimation model that recovers a metric scale 3D point map of a scene from a single image. Our method builds upon the recent monocular geometry estimation approach, MoGe, which predicts affine-invariant point maps with unknown scales. We explore effective strategies to extend MoGe for metric geometry prediction without compromising the relative geometry accuracy provided by the affine-invariant point representation. Additionally, we discover that noise and errors in real data diminish fine-grained detail in the predicted geometry. We address this by developing a unified data refinement approach that filters and completes real data from different sources using sharp synthetic labels, significantly enhancing the granularity of the reconstructed geometry while maintaining the overall accuracy. We train our model on a large corpus of mixed datasets and conducted comprehensive evaluations, demonstrating its superior performance in achieving accurate relative geometry, precise metric scale, and fine-grained detail recovery -- capabilities that no previous methods have simultaneously achieved.

Key facts. Cited by 250 papers in the map (data through 7 Oct 2026). Builds on 73 of its 83 references that are in the map. First posted on arXiv 3 Jul 2025.

Builds on

73 of 83 references.

References · 73

  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. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2023Segment Anythingcited by 8,158
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  8. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  9. 2021Vision Transformers for Dense Predictioncited by 1,789
  10. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  11. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  12. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
38 more
  1. 2024Depth Anything V2cited by 1,385
  2. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  3. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  5. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  6. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  7. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  8. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  9. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  10. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  11. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  12. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  13. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  14. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  15. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 593
  16. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  17. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  18. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  19. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 442
  20. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  21. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  22. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  23. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  24. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 373
  25. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  26. 2017Sparsity Invariant CNNscited by 325
  27. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 323
  28. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 320
  29. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 290
  30. 2019Structured3D: A Large Photo-realistic Dataset for Structured 3D Modelingcited by 285
  31. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
  32. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  33. 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 236
  34. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  35. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
  36. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 214
  37. 2024WonderWorld: Interactive 3D Scene Generation from a Single Imagecited by 197
  38. 2020A2D2: Audi Autonomous Driving Datasetcited by 189

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 53; 2026: 197.

250 papers.

Sort:

By area:

  1. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  2. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 292
  3. 2025MotionStream: Real-Time Video Generation with Interactive Motion Controlscited by 71
  4. 2025Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videoscited by 63
  5. 2026SAM 3D Body: Robust Full-Body Human Mesh Recoverycited by 61
  6. 2025OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modelingcited by 59
  7. 2026SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformercited by 50
  8. 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformerscited by 47
  9. 2026Image Generators are Generalist Vision Learnerscited by 40
  10. 2026HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worldscited by 34
  11. 2025DepthLM: Metric Depth From Vision Language Modelscited by 29
  12. 2025N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Modelscited by 28
38 more
  1. 2025TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Roboticscited by 27
  2. 2026VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Controlcited by 26
  3. 2025Geometrically-Constrained Agent for Spatial Reasoningcited by 25
  4. 2025Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimationcited by 24
  5. 2026Masked Depth Modeling for Spatial Perceptioncited by 24
  6. 2025DA2: Depth Anything in Any Directioncited by 22
  7. 2025DVGT: Driving Visual Geometry Transformercited by 20
  8. 2025Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenescited by 19
  9. 2025MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Expertscited by 19
  10. 2026InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fieldscited by 19
  11. 2025iLRM: An Iterative Large 3D Reconstruction Modelcited by 18
  12. 2025Reasoning in Space via Grounding in the Worldcited by 18
  13. 2026RealWonder: Real-Time Physical Action-Conditioned Video Generationcited by 18
  14. 2025Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Modelcited by 16
  15. 2026WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memoriescited by 15
  16. 2026Vista4D: Video Reshooting with 4D Point Cloudscited by 15
  17. 2025CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interactioncited by 14
  18. 2025Towards Spatial Trace with Reasoning in Vision-Language Models for Roboticscited by 12
  19. 2026DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scalecited by 12
  20. 2026WildDet3D: Scaling Promptable 3D Detection in the Wildcited by 12
  21. 2025Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robotscited by 11
  22. 2026EgoSim: Egocentric World Simulator for Embodied Interaction Generationcited by 11
  23. 2026NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Resultscited by 11
  24. 2026Track4World: Feedforward World-centric Dense 3D Tracking of All Pixelscited by 10
  25. 2025Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Trackingcited by 9
  26. 2026NavDreamer: Video Models as Zero-Shot 3D Navigatorscited by 9
  27. 20263D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Imagecited by 9
  28. 2026Do as I Do: Dexterous Manipulation Data from Everyday Human Videoscited by 9
  29. 2025UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstructioncited by 8
  30. 2025EgoX: Egocentric Video Generation from a Single Exocentric Videocited by 8
  31. 2026Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstructioncited by 8
  32. 2026MLLM-4D: Towards Visual-based Spatial-Temporal Intelligencecited by 8
  33. 2026MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Datacited by 8
  34. 2026WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Modelscited by 8
  35. 2025Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videoscited by 7
  36. 2026NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planningcited by 7
  37. 2026UniDAC: Universal Metric Depth Estimation for Any Cameracited by 7
  38. 2025ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learningcited by 6

50 most cited of 250 All 250 (JSON)