mlsanityData to 7 Oct 2026

Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes

arXiv 1904.11112 ↗First posted 25 Apr 2019cs.CVcited by 73

Not on the map. Why?

Abstract (arXiv)

We present a fully data-driven method to compute depth from diverse monocular video sequences that contain large amounts of non-rigid objects, e.g., people. In order to learn reconstruction cues for non-rigid scenes, we introduce a new dataset consisting of stereo videos scraped in-the-wild. This dataset has a wide variety of scene types, and features large amounts of nonrigid objects, especially people. From this, we compute disparity maps to be used as supervision to train our approach. We propose a loss function that allows us to generate a depth prediction even with unknown camera intrinsics and stereo baselines in the dataset. We validate the use of large amounts of Internet video by evaluating our method on existing video datasets with depth supervision, including SINTEL, and KITTI, and show that our approach generalizes better to natural scenes.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 14; 2023: 20; 2024: 14; 2025: 6; 2026: 5.

73 papers.

Sort:

By area:

  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  3. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  4. 2022Kubric: A scalable dataset generatorcited by 373
  5. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 202
  6. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 173
  7. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Viewscited by 148
  8. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 147
  9. 2024Stereo4D: Learning How Things Move in 3D from Internet Stereo Videoscited by 89
  10. 2021Neural Trajectory Fields for Dynamic Novel View Synthesiscited by 85
  11. 2021Multi-Task Self-Training for Learning General Representationscited by 85
  12. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 73
38 more
  1. 2023Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Taskscited by 72
  2. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  3. 2024DELTA: Dense Efficient Long-range 3D Tracking for any videocited by 62
  4. 2021360MonoDepth: High-Resolution 360deg Monocular Depth Estimationcited by 60
  5. 2021Consistent Depth of Moving Objects in Videocited by 56
  6. 2022Hierarchical Normalization for Robust Monocular Depth Estimationcited by 51
  7. 2022SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenescited by 50
  8. 2021Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Predictioncited by 48
  9. 2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptionscited by 47
  10. 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformerscited by 47
  11. 2023DITTO-NeRF: Diffusion-based Iterative Text To Omni-directional 3D Modelcited by 43
  12. 2021Toward Practical Monocular Indoor Depth Estimationcited by 42
  13. 2022Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Imagecited by 42
  14. 2023Flow supervision for Deformable NeRFcited by 42
  15. 2023EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimationcited by 42
  16. 2021Self-Supervised Multi-Frame Monocular Scene Flowcited by 29
  17. 2021Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learningcited by 19
  18. 2025DepthMaster: Taming Diffusion Models for Monocular Depth Estimationcited by 18
  19. 2022Improving Monocular Visual Odometry Using Learned Depthcited by 17
  20. 2022Depth Map Decomposition for Monocular Depth Estimationcited by 16
  21. 2024ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimationcited by 15
  22. 2022PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentationcited by 14
  23. 2023PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain Gap Using Pose-Preserved Text-to-Image Diffusioncited by 12
  24. 2023The Second Monocular Depth Estimation Challengecited by 12
  25. 2023Temporally Consistent Online Depth Estimation Using Point-Based Fusioncited by 12
  26. 2023SAAM: Stealthy Adversarial Attack on Monocular Depth Estimationcited by 12
  27. 2022A Survey on RGB-D Datasetscited by 11
  28. 2022Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depthcited by 11
  29. 2021Embedding Novel Views in a Single JPEG Imagecited by 10
  30. 2024The Third Monocular Depth Estimation Challengecited by 10
  31. 2021Estimating Image Depth in the Comics Domaincited by 8
  32. 2021THE Benchmark: Transferable Representation Learning for Monocular Height Estimationcited by 8
  33. 2023Salient Object Detection in RGB-D Videoscited by 8
  34. 2024ImmersePro: End-to-End Stereo Video Synthesis Via Implicit Disparity Learningcited by 8
  35. 2025The Fourth Monocular Depth Estimation Challengecited by 8
  36. 2023Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Datacited by 6
  37. 2023NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimationcited by 6
  38. 2023Robust Geometry-Preserving Depth Estimation Using Differentiable Renderingcited by 6

50 most cited of 73 All 73 (JSON)