mlsanityData to 7 Oct 2026

Robust Consistent Video Depth Estimation

arXiv 2012.05901 ↗First posted 10 Dec 2020cs.CVcited by 188

Not on the map. Why?

Abstract (arXiv)

We present an algorithm for estimating consistent dense depth maps and camera poses from a monocular video. We integrate a learning-based depth prior, in the form of a convolutional neural network trained for single-image depth estimation, with geometric optimization, to estimate a smooth camera trajectory as well as detailed and stable depth reconstruction. Our algorithm combines two complementary techniques: (1) flexible deformation-splines for low-frequency large-scale alignment and (2) geometry-aware depth filtering for high-frequency alignment of fine depth details. In contrast to prior approaches, our method does not require camera poses as input and achieves robust reconstruction for challenging hand-held cell phone captures containing a significant amount of noise, shake, motion blur, and rolling shutter deformations. Our method quantitatively outperforms state-of-the-arts on the Sintel benchmark for both depth and pose estimations and attains favorable qualitative results across diverse wild datasets.

Key facts. Cited by 188 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 28; 2023: 27; 2024: 35; 2025: 61; 2026: 29.

188 papers.

Sort:

By area:

  1. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  2. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  3. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  4. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  5. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  6. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
  7. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  8. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  9. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
  10. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 202
  11. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 202
  12. 2023Robust Dynamic Radiance Fieldscited by 193
38 more
  1. 2024PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generationcited by 185
  2. 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 177
  3. 2023SceneScape: Text-Driven Consistent Scene Generationcited by 160
  4. 2022NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fieldscited by 151
  5. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 147
  6. 2025Streaming 4D Visual Geometry Transformercited by 147
  7. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 122
  8. 2022P3Depth: Monocular Depth Estimation with a Piecewise Planarity Priorcited by 106
  9. 2023Progressively Optimized Local Radiance Fields for Robust View Synthesiscited by 103
  10. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  11. 2025Aether: Geometric-Aware Unified World Modelingcited by 94
  12. 2022ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wildcited by 90
  13. 2024Stereo4D: Learning How Things Move in 3D from Internet Stereo Videoscited by 89
  14. 2021T"oRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesiscited by 88
  15. 2025Easi3R: Estimating Disentangled Motion from DUSt3R Without Trainingcited by 88
  16. 2025St4RTrack: Simultaneous 4D Reconstruction and Tracking in the Worldcited by 88
  17. 2025SpatialTrackerV2: 3D Point Tracking Made Easycited by 84
  18. 2025Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memorycited by 82
  19. 2024Align3R: Aligned Monocular Depth Estimation for Dynamic Videoscited by 79
  20. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 76
  21. 2024TAPVid-3D: A Benchmark for Tracking Any Point in 3Dcited by 69
  22. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 66
  23. 2024DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videoscited by 63
  24. 2024DELTA: Dense Efficient Long-range 3D Tracking for any videocited by 62
  25. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
  26. 2021Consistent Depth of Moving Objects in Videocited by 56
  27. 2024LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometrycited by 54
  28. 2022Source-free Depth for Object Pop-outcited by 52
  29. 2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptionscited by 47
  30. 2021Toward Practical Monocular Indoor Depth Estimationcited by 42
  31. 2023Flow supervision for Deformable NeRFcited by 42
  32. 2022Monocular 3D Object Detection with Depth from Motioncited by 38
  33. 2023FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flowcited by 38
  34. 2024StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videoscited by 36
  35. 2025GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priorscited by 36
  36. 2025On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Imagescited by 35
  37. 2024Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completioncited by 32
  38. 2025Any4D: Unified Feed-Forward Metric 4D Reconstructioncited by 32

50 most cited of 188 All 188 (JSON)