mlsanityData to 7 Oct 2026

Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation

arXiv 1808.01838 ↗First posted 6 Aug 2018cs.CVcited by 69

Not on the map. Why?

Abstract (arXiv)

Occlusions play an important role in disparity and optical flow estimation, since matching costs are not available in occluded areas and occlusions indicate depth or motion boundaries. Moreover, occlusions are relevant for motion segmentation and scene flow estimation. In this paper, we present an efficient learning-based approach to estimate occlusion areas jointly with disparities or optical flow. The estimated occlusions and motion boundaries clearly improve over the state-of-the-art. Moreover, we present networks with state-of-the-art performance on the popular KITTI benchmark and good generic performance. Making use of the estimated occlusions, we also show improved results on motion segmentation and scene flow estimation.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 17; 2023: 9; 2024: 8; 2025: 4; 2026: 7.

69 papers.

Sort:

By area:

  1. 2021SMD-Nets: Stereo Mixture Density Networkscited by 118
  2. 2021MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matchingcited by 82
  3. 2023MFT: Long-Term Tracking of Every Pixelcited by 61
  4. 2022Learning Dense and Continuous Optical Flow from an Event Cameracited by 59
  5. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 51
  6. 2022Learning Pixel Trajectories with Multiscale Contrastive Random Walkscited by 36
  7. 2023Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervisioncited by 36
  8. 2022Learning Optical Flow, Depth, and Scene Flow without Real-World Labelscited by 31
  9. 2022What Matters for 3D Scene Flow Networkcited by 31
  10. 2021FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Cloudscited by 30
  11. 2023Fully neuromorphic vision and control for autonomous drone flightcited by 30
  12. 2021Self-Supervised Multi-Frame Monocular Scene Flowcited by 29
38 more
  1. 2021Fast Training of Neural Lumigraph Representations using Meta Learningcited by 29
  2. 2023OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baselinecited by 28
  3. 2023RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimationcited by 26
  4. 2021SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimationcited by 23
  5. 2024A Survey on Deep Stereo Matching in the Twentiescited by 23
  6. 2021Binary TTC: A Temporal Geofence for Autonomous Navigationcited by 20
  7. 2021Neural Disparity Refinement for Arbitrary Resolution Stereocited by 20
  8. 2025Zero-Shot Monocular Scene Flow Estimation in the Wildcited by 20
  9. 2021VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residualscited by 17
  10. 2021Residual 3D Scene Flow Learning with Context-Aware Feature Extractioncited by 15
  11. 2023CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoningcited by 15
  12. 2022ChiTransformer:Towards Reliable Stereo from Cuescited by 14
  13. 2022Optical Flow Training under Limited Label Budget via Active Learningcited by 14
  14. 2022Self-supervised Amodal Video Object Segmentationcited by 14
  15. 2022RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Cloudscited by 13
  16. 2021Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Cloudscited by 11
  17. 2021FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networkscited by 11
  18. 2022NanoFlowNet: Real-time Dense Optical Flow on a Nano Quadcoptercited by 10
  19. 2026Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazingcited by 8
  20. 2022Unsupervised Learning of 3D Scene Flow from Monocular Cameracited by 7
  21. 20223D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motioncited by 7
  22. 2025What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?cited by 7
  23. 2022RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluationcited by 6
  24. 2022DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustmentcited by 6
  25. 2021ORStereo: Occlusion-Aware Recurrent Stereo Matching for 4K-Resolution Imagescited by 5
  26. 2023Learning to Estimate Single-View Volumetric Flow Motions without 3D Supervisioncited by 5
  27. 2023The Drunkard's Odometry: Estimating Camera Motion in Deforming Scenescited by 5
  28. 2024SDGE: Stereo Guided Depth Estimation for 360^circ Camera Setscited by 5
  29. 2021Blocks World Revisited: The Effect of Self-Occlusion on Classification by Convolutional Neural Networkscited by 4
  30. 2021Detail Preserving Residual Feature Pyramid Modules for Optical Flowcited by 4
  31. 2021Sensor-Guided Optical Flowcited by 4
  32. 2021Joint Detection of Motion Boundaries and Occlusionscited by 4
  33. 2021DCVNet: Dilated Cost Volume Networks for Fast Optical Flowcited by 3
  34. 2021Self-Supervised Approach for Facial Movement Based Optical Flowcited by 3
  35. 2022Learning Scene Flow in 3D Point Clouds with Noisy Pseudo Labelscited by 3
  36. 2022Unsupervised Flow Refinement near Motion Boundariescited by 3
  37. 2022GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flowcited by 3
  38. 2021L3C-Stereo: Lossless Compression for Stereo Imagescited by 2

50 most cited of 69 All 69 (JSON)