mlsanityData to 7 Oct 2026

Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer

arXiv 1907.01341 ↗First posted 2 Jul 2019cs.CVcited by 1,484

Not on the map. Why?

Cited by 236 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different environments at scale, a number of datasets with distinct characteristics and biases have emerged. We develop tools that enable mixing multiple datasets during training, even if their annotations are incompatible. In particular, we propose a robust training objective that is invariant to changes in depth range and scale, advocate the use of principled multi-objective learning to combine data from different sources, and highlight the importance of pretraining encoders on auxiliary tasks. Armed with these tools, we experiment with five diverse training datasets, including a new, massive data source: 3D films. To demonstrate the generalization power of our approach we use zero-shot cross-dataset transfer}, i.e. we evaluate on datasets that were not seen during training. The experiments confirm that mixing data from complementary sources greatly improves monocular depth estimation. Our approach clearly outperforms competing methods across diverse datasets, setting a new state of the art for monocular depth estimation. Some results are shown in the supplementary video at https://youtu.be/D46FzVyL9I8

Key facts. Cited by 1,484 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 96; 2022: 146; 2023: 299; 2024: 388; 2025: 326; 2026: 229.

1,484 papers.

Sort:

By area:

  1. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  2. 2021Vision Transformers for Dense Predictioncited by 1,789
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  4. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  5. 2024Depth Anything V2cited by 1,385
  6. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  7. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  8. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  9. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  10. 2025Qwen-Image Technical Reportcited by 973
  11. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  12. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
38 more
  1. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
  2. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  3. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  4. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 591
  5. 2023Structure and Content-Guided Video Synthesis with Diffusion Modelscited by 589
  6. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  7. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 479
  8. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  9. 2025VACE: All-in-One Video Creation and Editingcited by 467
  10. 2023VideoComposer: Compositional Video Synthesis with Motion Controllabilitycited by 461
  11. 2023GLaMM: Pixel Grounding Large Multimodal Modelcited by 447
  12. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  13. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  14. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
  15. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  16. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  17. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  18. 2023Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Modelscited by 358
  19. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  20. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 356
  21. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  22. 2023ControlVideo: Training-free Controllable Text-to-Video Generationcited by 324
  23. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 323
  24. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 322
  25. 2023Pix2Video: Video Editing using Image Diffusioncited by 318
  26. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 305
  27. 2023Composer: Creative and Controllable Image Synthesis with Composable Conditionscited by 303
  28. 2023Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Actioncited by 301
  29. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  30. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 290
  31. 2022MultiMAE: Multi-modal Multi-task Masked Autoencoderscited by 287
  32. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
  33. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  34. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  35. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  36. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  37. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 250
  38. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235

50 most cited of 1,484 All 1,484 (JSON)