mlsanityData to 7 Oct 2026

VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residuals

arXiv 2104.06789 ↗First posted 14 Apr 2021cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

We propose a dense indirect visual odometry method taking as input externally estimated optical flow fields instead of hand-crafted feature correspondences. We define our problem as a probabilistic model and develop a generalized-EM formulation for the joint inference of camera motion, pixel depth, and motion-track confidence. Contrary to traditional methods assuming Gaussian-distributed observation errors, we supervise our inference framework under an (empirically validated) adaptive log-logistic distribution model. Moreover, the log-logistic residual model generalizes well to different state-of-the-art optical flow methods, making our approach modular and agnostic to the choice of optical flow estimators. Our method achieved top-ranking results on both TUM RGB-D and KITTI odometry benchmarks. Our open-sourced implementation is inherently GPU-friendly with only linear computational and storage growth.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 46 of its 105 references that are in the map. First posted on arXiv 14 Apr 2021.

Builds on

46 of 105 references.

References · 46

  1. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  2. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  3. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  4. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  5. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  6. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  7. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  8. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  9. 2018Pyramid Stereo Matching Networkcited by 486
  10. 2016Direct Sparse Odometrycited by 479
  11. 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
  12. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
34 more
  1. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  2. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 242
  3. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  4. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 200
  5. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  6. 2017DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networkscited by 173
  7. 2018BA-Net: Dense Bundle Adjustment Networkcited by 173
  8. 2018Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstructioncited by 159
  9. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  10. 2017CNN-SLAM: Real-time dense monocular SLAM with learned depth predictioncited by 152
  11. 2018CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAMcited by 151
  12. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  13. 2019Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentationcited by 141
  14. 2019Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimationcited by 131
  15. 2019Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Cameracited by 130
  16. 2019SelFlow: Self-Supervised Learning of Optical Flowcited by 128
  17. 2017Occlusion Aware Unsupervised Learning of Optical Flowcited by 101
  18. 2018Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometrycited by 85
  19. 2015EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flowcited by 80
  20. 2018Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimationcited by 69
  21. 2018Learning Monocular Depth by Distilling Cross-domain Stereo Networkscited by 64
  22. 2019Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depthcited by 50
  23. 2017An Efficient Algebraic Solution to the Perspective-Three-Point Problemcited by 29
  24. 2019Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenescited by 29
  25. 2018LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereocited by 28
  26. 2019Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometrycited by 27
  27. 2017Optical Flow in Mostly Rigid Scenescited by 20
  28. 2019Sequential Adversarial Learning for Self-Supervised Deep Visual Odometrycited by 18
  29. 2018CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Predictioncited by 17
  30. 2018Direct Sparse Odometry with Rolling Shuttercited by 12
  31. 2018Conditional Prior Networks for Optical Flowcited by 11
  32. 2018Learning monocular visual odometry with dense 3D mapping from dense 3D flowcited by 8
  33. 2019VITAMIN-E: VIsual Tracking And MappINg with Extremely Dense Feature Pointscited by 8
  34. 2016Fast, Robust, Continuous Monocular Egomotion Computationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 3; 2024: 2; 2025: 3; 2026: 1.

17 papers.

Sort:

  1. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  2. 2022Deep Patch Visual Odometrycited by 186
  3. 2022ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wildcited by 90
  4. 2022PanoFlow: Learning 360deg Optical Flow for Surrounding Temporal Understandingcited by 26
  5. 2021Efficient 3D Deep LiDAR Odometrycited by 25
  6. 2022LASER: LAtent SpacE Rendering for 2D Visual Localizationcited by 23
  7. 2023Deep Learning for Camera Calibration and Beyond: A Surveycited by 20
  8. 2022CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Drivingcited by 16
  9. 2023NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localizationcited by 13
  10. 2023Context-PIPs: Persistent Independent Particles Demands Spatial Context Featurescited by 9
  11. 2024Cross-Modal Semi-Dense 6-DoF Tracking of an Event Camera in Challenging Conditionscited by 9
  12. 2021NccFlow: Unsupervised Learning of Optical Flow With Non-occlusion from Geometrycited by 3
5 more
  1. 2025EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Flycited by 3
  2. 2025Perturbed State Space Feature Encoders for Optical Flow with Event Camerascited by 2
  3. 2025Optical Flow-Guided 6DoF Object Pose Tracking with an Event Cameracited by 2
  4. 2024From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layerscited by 1
  5. 2026GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlowcited by 0