mlsanityData to 7 Oct 2026

GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimation

arXiv 2510.18291 ↗First posted 21 Oct 2025cs.CVcited by 0

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

We introduce a novel framework for metric depth estimation that enhances pretrained diffusion-based monocular depth estimation (DB-MDE) models with stereo vision guidance. While existing DB-MDE methods excel at predicting relative depth, estimating absolute metric depth remains challenging due to scale ambiguities in single-image scenarios. To address this, we reframe depth estimation as an inverse problem, leveraging pretrained latent diffusion models (LDMs) conditioned on RGB images, combined with stereo-based geometric constraints, to learn scale and shift for accurate depth recovery. Our training-free solution seamlessly integrates into existing DB-MDE frameworks and generalizes across indoor, outdoor, and complex environments. Extensive experiments demonstrate that our approach matches or surpasses state-of-the-art methods, particularly in challenging scenarios involving translucent and specular surfaces, all without requiring retraining.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 53 of its 65 references that are in the map. First posted on arXiv 21 Oct 2025.

Builds on

53 of 65 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation27 Mar
  2. 2024DepthFM: Fast Monocular Depth Estimation with Flow Matching20 Mar
  3. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image18 Mar
  4. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation2 Jun
  5. 2023Monocular Depth Estimation using Diffusion Models28 Feb

Other references · 48

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  7. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  8. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  9. 2024Depth Anything V2cited by 1,385
  10. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  11. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  12. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
36 more
  1. 2022Denoising Diffusion Restoration Modelscited by 951
  2. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  3. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  4. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  5. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  6. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  7. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  8. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 501
  9. 2018Pyramid Stereo Matching Networkcited by 486
  10. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  11. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  12. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  13. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  14. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  15. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 348
  16. 2019Group-wise Correlation Stereo Networkcited by 235
  17. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 188
  18. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistencycited by 180
  19. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 173
  20. 2024A Survey on Diffusion Models for Inverse Problemscited by 173
  21. 2024Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Predictioncited by 163
  22. 2023DDP: Diffusion Model for Dense Visual Predictioncited by 148
  23. 2022Attention Concatenation Volume for Accurate and Efficient Stereo Matchingcited by 130
  24. 2023DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimationcited by 81
  25. 2023MagicEdit: High-Fidelity and Temporally Coherent Video Editingcited by 75
  26. 2019Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learningcited by 60
  27. 2019Learning to Adapt for Stereocited by 42
  28. 2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfacescited by 33
  29. 2024GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereocited by 16
  30. 2024Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learningcited by 12
  31. 2019Online Adaptation through Meta-Learning for Stereo Depth Estimationcited by 7
  32. 2023Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstructioncited by 7
  33. 2023Hybrid Neural Diffeomorphic Flow for Shape Representation and Generation via Triplanecited by 6
  34. 2024RobustMVS: Single Domain Generalized Deep Multi-view Stereocited by 5
  35. 2023Hybrid-CSR: Coupling Explicit and Implicit Shape Representation for Cortical Surface Reconstructioncited by 3
  36. 2024nvTorchCam: An Open-source Library for Camera-Agnostic Differentiable Geometric Visioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model
  2. 2025VistaDepth: Improving far-range Depth Estimation with Spectral Modulation and Adaptive Reweighting
  3. 2024GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion
  4. 2024D4D: An RGBD diffusion model to boost monocular depth estimation
  5. 2024MetricGold: Leveraging Text-To-Image Latent Diffusion Models for Metric Depth Estimation
  6. 2025StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation
  7. 2026GeoStereo: A Unified Stereo Geometry Estimation Framework for Disparity and Surface Normal
  8. 2024SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation