mlsanityData to 14 Oct 2026

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second

arXiv 2410.02073 ↗First posted 2 Oct 2024cs.CV cs.LGcited by 404

Not on the map. Why?

Cited by 41 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a foundation model for zero-shot metric monocular depth estimation. Our model, Depth Pro, synthesizes high-resolution depth maps with unparalleled sharpness and high-frequency details. The predictions are metric, with absolute scale, without relying on the availability of metadata such as camera intrinsics. And the model is fast, producing a 2.25-megapixel depth map in 0.3 seconds on a standard GPU. These characteristics are enabled by a number of technical contributions, including an efficient multi-scale vision transformer for dense prediction, a training protocol that combines real and synthetic datasets to achieve high metric accuracy alongside fine boundary tracing, dedicated evaluation metrics for boundary accuracy in estimated depth maps, and state-of-the-art focal length estimation from a single image. Extensive experiments analyze specific design choices and demonstrate that Depth Pro outperforms prior work along multiple dimensions. We release code and weights at https://github.com/apple/ml-depth-pro

Key facts. Cited by 404 papers in the map (data through 14 Oct 2026). Builds on 98 of its 122 references that are in the map. First posted on arXiv 2 Oct 2024.

Builds on

98 of 122 references.

References · 98

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2023Segment Anythingcited by 8,234
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  8. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  9. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  10. 2022A ConvNet for the 2020scited by 3,579
  11. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  12. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
38 more
  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  2. 2021Vision Transformers for Dense Predictioncited by 1,803
  3. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  4. 2024Depth Anything V2cited by 1,422
  5. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  7. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  8. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  9. 2021Multiscale Vision Transformerscited by 897
  10. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  11. 2023EVA-CLIP: Improved Training Techniques for CLIP at Scalecited by 798
  12. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  13. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  14. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
  15. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  16. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  17. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 629
  18. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  19. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  20. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  21. 2022Vision Transformer Adapter for Dense Predictionscited by 565
  22. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  23. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  24. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  25. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  26. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  27. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
  28. 2022DeiT III: Revenge of the ViTcited by 419
  29. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  30. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 382
  31. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
  32. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 341
  33. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 327
  34. 2022BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizerscited by 303
  35. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  36. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 236
  37. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
  38. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206

50 most cited of 98 All 98 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 26; 2025: 200; 2026: 178.

404 papers.

Sort:

By area:

  1. 2025Qwen-Image Technical Reportcited by 1,044
  2. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  3. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  4. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 314
  5. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 261
  6. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 173
  7. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 173
  8. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 170
  9. 2025Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noisecited by 117
  10. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 110
  11. 2025Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridgingcited by 99
  12. 2025CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Modelscited by 98
38 more
  1. 2025Aether: Geometric-Aware Unified World Modelingcited by 97
  2. 2024Stereo4D: Learning How Things Move in 3D from Internet Stereo Videoscited by 89
  3. 2024Align3R: Aligned Monocular Depth Estimation for Dynamic Videoscited by 79
  4. 2025Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysiscited by 78
  5. 2025Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generationcited by 77
  6. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 74
  7. 2025MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMscited by 73
  8. 2025Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generationcited by 67
  9. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 62
  10. 2025UniK3D: Universal Camera Monocular 3D Estimationcited by 62
  11. 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformerscited by 51
  12. 2024Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusioncited by 50
  13. 2025UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobilitycited by 49
  14. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 47
  15. 2025SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoningcited by 46
  16. 2026NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videoscited by 46
  17. 2026Image Generators are Generalist Vision Learnerscited by 43
  18. 2025DICEPTION: A Generalist Diffusion Model for Visual Perceptual Taskscited by 39
  19. 2024VistaDream: Sampling multiview consistent images for single-view scene reconstructioncited by 38
  20. 2025FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesiscited by 37
  21. 2025GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priorscited by 37
  22. 2025LBM: Latent Bridge Matching for Fast Image-to-Image Translationcited by 36
  23. 2025Depth Anything with Any Priorcited by 36
  24. 2025TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigationcited by 36
  25. 2025MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Secondcited by 35
  26. 2025Matrix-3D: Omnidirectional Explorable 3D World Generationcited by 35
  27. 2025Detect Anything 3D in the Wildcited by 33
  28. 2025EgoZero: Robot Learning from Smart Glassescited by 33
  29. 2024MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Modelcited by 32
  30. 2024OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integrationcited by 30
  31. 2025DepthLM: Metric Depth From Vision Language Modelscited by 30
  32. 2024Video Depth without Video Modelscited by 29
  33. 2025Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Videocited by 29
  34. 2026OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulationcited by 28
  35. 2024DepthLab: From Partial to Completecited by 27
  36. 2025Dynamic Camera Poses and Where to Find Themcited by 27
  37. 2025MVSAnywhere: Zero-Shot Multi-View Stereocited by 26
  38. 2025MP-SfM: Monocular Surface Priors for Robust Structure-from-Motioncited by 26

50 most cited of 404 All 404 (JSON)