mlsanityData to 14 Oct 2026

EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow

arXiv 1501.02565 ↗First posted 12 Jan 2015cs.CVcited by 80

Not on the map. Why?

Abstract (arXiv)

We propose a novel approach for optical flow estimation , targeted at large displacements with significant oc-clusions. It consists of two steps: i) dense matching by edge-preserving interpolation from a sparse set of matches; ii) variational energy minimization initialized with the dense matches. The sparse-to-dense interpolation relies on an appropriate choice of the distance, namely an edge-aware geodesic distance. This distance is tailored to handle occlusions and motion boundaries -- two common and difficult issues for optical flow computation. We also propose an approximation scheme for the geodesic distance to allow fast computation without loss of performance. Subsequent to the dense interpolation step, standard one-level variational energy minimization is carried out on the dense matches to obtain the final flow estimation. The proposed approach, called Edge-Preserving Interpolation of Correspondences (EpicFlow) is fast and robust to large displacements. It significantly outperforms the state of the art on MPI-Sintel and performs on par on Kitti and Middlebury.

Key facts. Cited by 80 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Jan 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 22; 2022: 12; 2023: 18; 2024: 14; 2025: 12; 2026: 2.

80 papers.

Sort:

By area:

  1. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  2. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 327
  3. 2022Unifying Flow, Stereo and Depth Estimationcited by 275
  4. 2021Learning to Estimate Hidden Motions with Global Motion Aggregationcited by 224
  5. 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
  6. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
  7. 2022Global Matching with Overlapping Attention for Optical Flow Estimationcited by 64
  8. 2023Dense Optical Tracking: Connecting the Dotscited by 61
  9. 2024MemFlow: Optical Flow Estimation and Prediction with Memorycited by 55
  10. 2021High-Resolution Optical Flow from 1D Attention and Correlationcited by 54
  11. 2022NAN: Noise-Aware NeRFs for Burst-Denoisingcited by 48
  12. 2021Adaptive Surface Normal Constraint for Depth Estimationcited by 43
38 more
  1. 2022Learning Pixel Trajectories with Multiscale Contrastive Random Walkscited by 36
  2. 2023Rethinking Optical Flow from Geometric Matching Consistent Perspectivecited by 33
  3. 2024DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detectioncited by 33
  4. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
  5. 2023Diffusion Model for Dense Matchingcited by 21
  6. 2021The Functional Correspondence Problemcited by 20
  7. 2023AccFlow: Backward Accumulation for Long-Range Optical Flowcited by 19
  8. 2021VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residualscited by 17
  9. 2022Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Surveycited by 17
  10. 2023Shape-Constraint Recurrent Flow for 6D Object Pose Estimationcited by 17
  11. 2022CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Drivingcited by 16
  12. 2024Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Imagescited by 14
  13. 2023Flow Dynamics Correction for Action Recognitioncited by 12
  14. 2024Taylor Videos for Action Recognitioncited by 12
  15. 2023Delving into Crispness: Guided Label Refinement for Crisp Edge Detectioncited by 11
  16. 2023FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimationcited by 10
  17. 2025FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Basescited by 10
  18. 2021Learning Scene Dynamics from Point Cloud Sequencescited by 9
  19. 2021ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Samplingcited by 8
  20. 2024Rethinking RAFT for Efficient Optical Flowcited by 8
  21. 2024Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?cited by 8
  22. 2025MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Trainingcited by 8
  23. 2021MUNet: Motion Uncertainty-aware Semi-supervised Video Object Segmentationcited by 7
  24. 2023SplatFlow: Learning Multi-frame Optical Flow via Splattingcited by 7
  25. 2021DeepOIS: Gyroscope-Guided Deep Optical Image Stabilizer Compensationcited by 6
  26. 2021Learning by Distillation: A Self-Supervised Learning Framework for Optical Flow Estimationcited by 6
  27. 2021EVReflex: Dense Time-to-Impact Prediction for Event-based Obstacle Avoidancecited by 6
  28. 2021PDC: Piecewise Depth Completion utilizing Superpixelscited by 5
  29. 2023FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous Drivingcited by 5
  30. 2021Sensor-Guided Optical Flowcited by 4
  31. 2023Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Headcited by 4
  32. 2024Adverse Weather Optical Flow: Cumulative Homogeneous-Heterogeneous Adaptationcited by 4
  33. 2021Target Detection and Segmentation in Circular-Scan Synthetic-Aperture-Sonar Images using Semi-Supervised Convolutional Encoder-Decoderscited by 3
  34. 2021FAMINet: Learning Real-time Semi-supervised Video Object Segmentation with Steepest Optimized Optical Flowcited by 3
  35. 2023Motion-state Alignment for Video Semantic Segmentationcited by 3
  36. 2024Towards Dependable Optical Flow: Benchmarks for Real-World Spatiotemporal Corruptionscited by 3
  37. 2025Online Dense Point Tracking with Streaming Memorycited by 3
  38. 2025Feature Hallucination for Self-supervised Action Recognitioncited by 3

50 most cited of 80 All 80 (JSON)