mlsanityData to 14 Oct 2026

DeepV2D: Video to Depth with Differentiable Structure from Motion

arXiv 1812.04605 ↗First posted 11 Dec 2018cs.CVcited by 185

Not on the map. Why?

Abstract (arXiv)

We propose DeepV2D, an end-to-end deep learning architecture for predicting depth from video. DeepV2D combines the representation ability of neural networks with the geometric principles governing image formation. We compose a collection of classical geometric algorithms, which are converted into trainable modules and combined into an end-to-end differentiable architecture. DeepV2D interleaves two stages: motion estimation and depth estimation. During inference, motion and depth estimation are alternated and converge to accurate depth. Code is available https://github.com/princeton-vl/DeepV2D.

Key facts. Cited by 185 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 20; 2022: 29; 2023: 29; 2024: 42; 2025: 43; 2026: 22.

185 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  2. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  3. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  4. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  5. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  6. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  7. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 314
  8. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 286
  9. 2022Unifying Flow, Stereo and Depth Estimationcited by 275
  10. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  11. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  12. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 205
38 more
  1. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 204
  2. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 192
  3. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 164
  4. 2025MUSt3R: Multi-view Network for Stereo 3D Reconstructioncited by 141
  5. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 138
  6. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 136
  7. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 133
  8. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  9. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 115
  10. 2024Learning Temporally Consistent Video Depth from Video Diffusion Priorscited by 100
  11. 2025DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planningcited by 94
  12. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  13. 2024Align3R: Aligned Monocular Depth Estimation for Dynamic Videoscited by 79
  14. 2024Large Spatial Model: End-to-end Unposed Images to Semantic 3Dcited by 73
  15. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 72
  16. 2024Deep Patch Visual SLAMcited by 71
  17. 2021Monocular 3D Object Detection: An Extrinsic Parameter Free Approachcited by 69
  18. 2022Theseus: A Library for Differentiable Nonlinear Optimizationcited by 65
  19. 2024World-consistent Video Diffusion with Explicit 3D Modelingcited by 65
  20. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  21. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
  22. 2024Depth Any Video with Scalable Synthetic Datacited by 57
  23. 2024LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometrycited by 56
  24. 2022Few-View Object Reconstruction with Unknown Categories and Camera Posescited by 53
  25. 2021Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometrycited by 46
  26. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
  27. 2025Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstructioncited by 44
  28. 2023Dense RGB SLAM with Neural Implicit Mapscited by 42
  29. 2023Flow supervision for Deformable NeRFcited by 42
  30. 2021Tangent Space Backpropagation for 3D Transformation Groupscited by 40
  31. 2025Matrix3D: Large Photogrammetry Model All-in-Onecited by 40
  32. 2021Deep Two-View Structure-from-Motion Revisitedcited by 39
  33. 2022A Benchmark and a Baseline for Robust Multi-view Depth Estimationcited by 39
  34. 2023R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Camerascited by 39
  35. 2021SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Datacited by 38
  36. 2021MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentscited by 38
  37. 2022RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimizationcited by 38
  38. 2022Monocular 3D Object Detection with Depth from Motioncited by 38

50 most cited of 185 All 185 (JSON)