mlsanityData to 14 Oct 2026

Consistent Video Depth Estimation

arXiv 2004.15021 ↗First posted 30 Apr 2020cs.CVcited by 220

Not on the map. Why?

Abstract (arXiv)

We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video. We leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video. Unlike the ad-hoc priors in classical reconstruction, we use a learning-based prior, i.e., a convolutional neural network trained for single-image depth estimation. At test time, we fine-tune this network to satisfy the geometric constraints of a particular input video, while retaining its ability to synthesize plausible depth details in parts of the video that are less constrained. We show through quantitative validation that our method achieves higher accuracy and a higher degree of geometric consistency than previous monocular reconstruction methods. Visually, our results appear more stable. Our algorithm is able to handle challenging hand-held captured input videos with a moderate degree of dynamic motion. The improved quality of the reconstruction enables several applications, such as scene reconstruction and advanced video-based visual effects.

Key facts. Cited by 220 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 31; 2022: 47; 2023: 43; 2024: 42; 2025: 41; 2026: 16.

220 papers.

Sort:

By area:

  1. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  2. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  3. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  4. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  5. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  6. 2024Learning to (Learn at Test Time): RNNs with Expressive Hidden Statescited by 355
  7. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 250
  8. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  9. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  10. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 228
  11. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  12. 2022Test-Time Training with Masked Autoencoderscited by 212
38 more
  1. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 207
  2. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 204
  3. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 192
  4. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  5. 2022Depth-Aware Generative Adversarial Network for Talking Head Video Generationcited by 178
  6. 2022Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-timecited by 165
  7. 2023SceneScape: Text-Driven Consistent Scene Generationcited by 160
  8. 2022NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fieldscited by 152
  9. 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
  10. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 148
  11. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 138
  12. 2021Layered Neural Atlases for Consistent Video Editingcited by 137
  13. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 129
  14. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  15. 2023Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fieldscited by 123
  16. 2021Capturing, Reconstructing, and Simulating: the UrbanScene3D Datasetcited by 118
  17. 2022Towards An End-to-End Framework for Flow-Guided Video Inpaintingcited by 113
  18. 2023Progressively Optimized Local Radiance Fields for Robust View Synthesiscited by 103
  19. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  20. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  21. 2025Easi3R: Estimating Disentangled Motion from DUSt3R Without Trainingcited by 91
  22. 2024Stereo4D: Learning How Things Move in 3D from Internet Stereo Videoscited by 89
  23. 2021T"oRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesiscited by 88
  24. 2021Neural Trajectory Fields for Dynamic Novel View Synthesiscited by 86
  25. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  26. 2024Align3R: Aligned Monocular Depth Estimation for Dynamic Videoscited by 79
  27. 2023Neural Residual Radiance Fields for Streamably Free-Viewpoint Videoscited by 77
  28. 2024TAPVid-3D: A Benchmark for Tracking Any Point in 3Dcited by 72
  29. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  30. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  31. 2025End-to-End Test-Time Training for Long Contextcited by 62
  32. 2024Depth Any Video with Scalable Synthetic Datacited by 57
  33. 2021Consistent Depth of Moving Objects in Videocited by 56
  34. 2022SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenescited by 52
  35. 2022Source-free Depth for Object Pop-outcited by 52
  36. 2024MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priorscited by 51
  37. 2021Toward Practical Monocular Indoor Depth Estimationcited by 42
  38. 2023Flow supervision for Deformable NeRFcited by 42

50 most cited of 220 All 220 (JSON)