mlsanityData to 7 Oct 2026

DeMoN: Depth and Motion Network for Learning Monocular Stereo

arXiv 1612.02401 ↗First posted 7 Dec 2016cs.CVcited by 200

Not on the map. Why?

Abstract (arXiv)

In this paper we formulate structure from motion as a learning problem. We train a convolutional network end-to-end to compute depth and camera motion from successive, unconstrained image pairs. The architecture is composed of multiple stacked encoder-decoder networks, the core part being an iterative network that is able to improve its own predictions. The network estimates not only depth and motion, but additionally surface normals, optical flow between the images and confidence of the matching. A crucial component of the approach is a training loss based on spatial relative differences. Compared to traditional two-frame structure from motion methods, results are more accurate and more robust. In contrast to the popular depth-from-single-image networks, DeMoN learns the concept of matching and, thus, better generalizes to structures not seen during training.

Key facts. Cited by 200 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 52; 2022: 39; 2023: 38; 2024: 33; 2025: 27; 2026: 11.

200 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  3. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  4. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  5. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  6. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  7. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  8. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  9. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  10. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  11. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  12. 2023Visual Geometry Grounded Deep Structure From Motioncited by 225
38 more
  1. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  2. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  3. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
  4. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 146
  5. 2025MUSt3R: Multi-view Network for Stereo 3D Reconstructioncited by 139
  6. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 137
  7. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 112
  8. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 107
  9. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  10. 2025Cameras as Relative Positional Encodingcited by 94
  11. 2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizercited by 73
  12. 2024Large Spatial Model: End-to-end Unposed Images to Semantic 3Dcited by 73
  13. 2021Monocular 3D Object Detection: An Extrinsic Parameter Free Approachcited by 69
  14. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 69
  15. 2024World-consistent Video Diffusion with Explicit 3D Modelingcited by 62
  16. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
  17. 2022Motion Inspired Unsupervised Perception and Prediction in Autonomous Drivingcited by 59
  18. 2024LightIt: Illumination Modeling and Control for Diffusion Modelscited by 56
  19. 2024VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstructioncited by 50
  20. 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learningcited by 49
  21. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
  22. 2021MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutionscited by 43
  23. 2025Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstructioncited by 43
  24. 2022Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Imagecited by 42
  25. 2023Dense RGB SLAM with Neural Implicit Mapscited by 42
  26. 2021Planar Surface Reconstruction from Sparse Viewscited by 40
  27. 2021Deep Two-View Structure-from-Motion Revisitedcited by 39
  28. 2025Matrix3D: Large Photogrammetry Model All-in-Onecited by 39
  29. 2021MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentscited by 38
  30. 2022A Benchmark and a Baseline for Robust Multi-view Depth Estimationcited by 38
  31. 2023NOPE: Novel Object Pose Estimation from a Single Imagecited by 38
  32. 2021Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervisioncited by 37
  33. 2025Detect Anything 3D in the Wildcited by 32
  34. 2021Projective Manifold Gradient Layer for Deep Rotation Regressioncited by 31
  35. 2021Input-level Inductive Biases for 3D Reconstructioncited by 31
  36. 2024GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstructioncited by 31
  37. 2023PMatch: Paired Masked Image Modeling for Dense Geometric Matchingcited by 29
  38. 2023Deep Event Visual Odometrycited by 29

50 most cited of 200 All 200 (JSON)