mlsanityData to 7 Oct 2026

MegaDepth: Learning Single-View Depth Prediction from Internet Photos

arXiv 1804.00607 ↗First posted 2 Apr 2018cs.CVcited by 731

Not on the map. Why?

Cited by 27 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Single-view depth prediction is a fundamental problem in computer vision. Recently, deep learning methods have led to significant progress, but such methods are limited by the available training data. Current datasets based on 3D sensors have key limitations, including indoor-only images (NYU), small numbers of training examples (Make3D), and sparse sampling (KITTI). We propose to use multi-view Internet photo collections, a virtually unlimited data source, to generate training data via modern structure-from-motion and multi-view stereo (MVS) methods, and present a large depth dataset called MegaDepth based on this idea. Data derived from MVS comes with its own challenges, including noise and unreconstructable objects. We address these challenges with new data cleaning methods, as well as automatically augmenting our data with ordinal depth relations generated using semantic segmentation. We validate the use of large amounts of Internet data by showing that models trained on MegaDepth exhibit strong generalization-not only to novel scenes, but also to other diverse datasets including Make3D, KITTI, and DIW, even when no images from those datasets are seen during training.

Key facts. Cited by 731 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 83; 2022: 99; 2023: 121; 2024: 119; 2025: 157; 2026: 152.

731 papers.

Sort:

By area:

  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  3. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  4. 2024Depth Anything V2cited by 1,385
  5. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  6. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  7. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  8. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  9. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  10. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  11. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  12. 2025Continuous 3D Perception Model with Persistent Statecited by 527
38 more
  1. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 442
  2. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  3. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 356
  4. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 323
  5. 2023RoMa: Robust Dense Feature Matchingcited by 296
  6. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  7. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 292
  8. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 290
  9. 2023TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinementcited by 281
  10. 20243D Reconstruction with Spatial Memorycited by 269
  11. 2022TAP-Vid: A Benchmark for Tracking Any Point in a Videocited by 258
  12. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 250
  13. 2023Visual Geometry Grounded Deep Structure From Motioncited by 225
  14. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
  15. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  16. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 199
  17. 2023Tracking Everything Everywhere All at Oncecited by 190
  18. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  19. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
  20. 2024Probing the 3D Awareness of Visual Foundation Modelscited by 175
  21. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 174
  22. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 173
  23. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  24. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 170
  25. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 169
  26. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
  27. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 165
  28. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 161
  29. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 158
  30. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Viewscited by 148
  31. 2025Streaming 4D Visual Geometry Transformercited by 147
  32. 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 144
  33. 2025MUSt3R: Multi-view Network for Stereo 3D Reconstructioncited by 139
  34. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  35. 2021Learning Target Candidate Association to Keep Track of What Not to Trackcited by 131
  36. 2022QuadTree Attention for Vision Transformerscited by 129
  37. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 129
  38. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126

50 most cited of 731 All 731 (JSON)