mlsanityData to 7 Oct 2026

Towards Zero-Shot Scale-Aware Monocular Depth Estimation

arXiv 2306.17253 ↗First posted 29 Jun 2023cs.CV cs.LGcited by 100

Not on the map. Why?

Abstract (arXiv)

Monocular depth estimation is scale-ambiguous, and thus requires scale supervision to produce metric predictions. Even so, the resulting models will be geometry-specific, with learned scales that cannot be directly transferred across domains. Because of that, recent works focus instead on relative depth, eschewing scale in favor of improved up-to-scale zero-shot transfer. In this work we introduce ZeroDepth, a novel monocular depth estimation framework capable of predicting metric scale for arbitrary test images from different domains and camera parameters. This is achieved by (i) the use of input-level geometric embeddings that enable the network to learn a scale prior over objects; and (ii) decoupling the encoder and decoder stages, via a variational latent representation that is conditioned on single frame information. We evaluated ZeroDepth targeting both outdoor (KITTI, DDAD, nuScenes) and indoor (NYUv2) benchmarks, and achieved a new state-of-the-art in both settings using the same pre-trained model, outperforming methods that train on in-domain data and require test-time scaling to produce metric estimates.

Key facts. Cited by 100 papers in the map (data through 7 Oct 2026). Builds on 51 of its 67 references that are in the map. First posted on arXiv 29 Jun 2023.

Builds on

51 of 67 references.

References · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  7. 2021Vision Transformers for Dense Predictioncited by 1,789
  8. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  9. 2016Variational Inference: A Review for Statisticianscited by 1,466
  10. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  11. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  12. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
38 more
  1. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  2. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  3. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  4. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  5. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  6. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  7. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  8. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  9. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  10. 2017Sparsity Invariant CNNscited by 325
  11. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  12. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  13. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 166
  14. 2020Feature-metric Loss for Self-supervised Learning of Depth and Egomotioncited by 140
  15. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  16. 2019DADA: Depth-aware Domain Adaptation in Semantic Segmentationcited by 97
  17. 2022Attention Attention Everywhere: Monocular Depth Prediction with Skip Attentioncited by 92
  18. 2022SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimationcited by 76
  19. 2019CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depthcited by 75
  20. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  21. 2019Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimationcited by 61
  22. 2019Unsupervised Scene Adaptation with Memory Regularization in vivocited by 57
  23. 2021Towards Real-Time Monocular Depth Estimation for Robotics: A Surveycited by 55
  24. 2023VA-DepthNet: A Variational Approach to Single Image Depth Predictioncited by 54
  25. 2018SPIGAN: Privileged Adversarial Learning from Simulationcited by 47
  26. 2021Toward Practical Monocular Indoor Depth Estimationcited by 42
  27. 2021Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completioncited by 39
  28. 2021MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentscited by 38
  29. 2021StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimationcited by 36
  30. 2021Geometric Unsupervised Domain Adaptation for Semantic Segmentationcited by 33
  31. 2021Input-level Inductive Biases for 3D Reconstructioncited by 31
  32. 2022Learning Optical Flow, Depth, and Scene Flow without Real-World Labelscited by 31
  33. 2021Monocular Depth Estimation through Virtual-world Supervision and Real-world SfM Self-Supervisioncited by 24
  34. 2020Self-Supervised Scale Recovery for Monocular Depth and Egomotion Estimationcited by 21
  35. 2021Self-Supervised Camera Self-Calibration from Videocited by 17
  36. 2022Depth Field Networks for Generalizable Multi-view Scene Representationcited by 17
  37. 2021Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimationcited by 16
  38. 2022MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentscited by 12

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 37; 2025: 35; 2026: 21.

100 papers.

Sort:

By area:

  1. 2024Depth Anything V2cited by 1,385
  2. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  3. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  4. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  5. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  6. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 323
  7. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 250
  8. 2024Sapiens: Foundation for Human Vision Modelscited by 229
  9. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 170
  10. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  11. 2025Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysiscited by 78
  12. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 73
38 more
  1. 2025UniK3D: Universal Camera Monocular 3D Estimationcited by 60
  2. 2023DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Imagecited by 48
  3. 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformerscited by 47
  4. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
  5. 2024Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentationcited by 38
  6. 2025Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Cameracited by 38
  7. 20233D Hand Pose Estimation in Everyday Egocentric Imagescited by 33
  8. 2023FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimatorscited by 29
  9. 2023Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Modelcited by 29
  10. 20243D-SceneDreamer: Text-Driven 3D-Consistent Scene Generationcited by 29
  11. 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditionscited by 29
  12. 2024Video Depth without Video Modelscited by 28
  13. 2024SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillationcited by 21
  14. 2024RadarCam-Depth: Radar-Camera Fusion for Depth Estimation with Learned Metric Scalecited by 20
  15. 2024RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptionscited by 20
  16. 2025Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generationcited by 17
  17. 2024ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimationcited by 15
  18. 2024Track Everything Everywhere Fast and Robustlycited by 13
  19. 2025Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimationcited by 13
  20. 2024Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoningcited by 12
  21. 2025Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusioncited by 12
  22. 2024HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priorscited by 11
  23. 2025Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robotscited by 11
  24. 2024The Third Monocular Depth Estimation Challengecited by 10
  25. 2026RayRoPE: Projective Ray Positional Encoding for Multi-view Attentioncited by 10
  26. 2026MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sourcescited by 10
  27. 2024Towards Robust Monocular Depth Estimation in Non-Lambertian Surfacescited by 9
  28. 2025The Fourth Monocular Depth Estimation Challengecited by 8
  29. 2025LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoningcited by 7
  30. 2025UnLoc: Leveraging Depth Uncertainties for Floorplan Localizationcited by 7
  31. 2026UniDAC: Universal Metric Depth Estimation for Any Cameracited by 7
  32. 2024CLIP Can Understand Depthcited by 6
  33. 2024GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusioncited by 6
  34. 2025Metric-Solver: Sliding Anchored Metric Depth Estimation from a Single Imagecited by 6
  35. 2025Towards In-the-wild 3D Plane Reconstruction from a Single Imagecited by 6
  36. 2024A Simple yet Effective Test-Time Adaptation for Zero-Shot Monocular Metric Depth Estimationcited by 5
  37. 2025Radar-Guided Polynomial Fitting for Metric Depth Estimationcited by 5
  38. 2025MonoTher-Depth: Enhancing Thermal Depth Estimation via Confidence-Aware Distillationcited by 5

50 most cited of 100 All 100 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimation
  2. 2025Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues
  3. 2026EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion Decoder
  4. 2026ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning
  5. 2025VistaDepth: Improving far-range Depth Estimation with Spectral Modulation and Adaptive Reweighting
  6. 2024PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage
  7. 2025Always Clear Depth: Robust Monocular Depth Estimation under Adverse Weather
  8. 2025Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior