mlsanityData to 7 Oct 2026

Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids

arXiv 1604.03513 ↗First posted 12 Apr 2016cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

We present a global optimization approach to optical flow estimation. The approach optimizes a classical optical flow objective over the full space of mappings between discrete grids. No descriptor matching is used. The highly regular structure of the space of mappings enables optimizations that reduce the computational complexity of the algorithm's inner loop from quadratic to linear and support efficient matching of tens of thousands of nodes to tens of thousands of displacements. We show that one-shot global optimization of a classical Horn-Schunck-type objective over regular grids at a single resolution is sufficient to initialize continuous interpolation and achieve state-of-the-art performance on challenging modern benchmarks.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 6; 2023: 6; 2024: 6; 2025: 6; 2026: 1.

34 papers.

Sort:

By area:

  1. 2021Learning to Estimate Hidden Motions with Global Motion Aggregationcited by 223
  2. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 169
  3. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  4. 2021SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warpingcited by 74
  5. 2022Global Matching with Overlapping Attention for Optical Flow Estimationcited by 64
  6. 2022Deep Equilibrium Optical Flow Estimationcited by 63
  7. 2022SKFlow: Learning Optical Flow with Super Kernelscited by 56
  8. 2021High-Resolution Optical Flow from 1D Attention and Correlationcited by 54
  9. 2021Learning Optical Flow from a Few Matchescited by 53
  10. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 32
  11. 2025WAFT: Warping-Alone Field Transforms for Optical Flowcited by 32
  12. 2021Learning optical flow from still imagescited by 28
22 more
  1. 2023DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Taskscited by 22
  2. 2023Shape-Constraint Recurrent Flow for 6D Object Pose Estimationcited by 17
  3. 2023SAMConvex: Fast Discrete Optimization for CT Registration using Self-supervised Anatomical Embedding and Correlation Pyramidcited by 14
  4. 2022Match Cutting: Finding Cuts with Smooth Visual Transitionscited by 12
  5. 2025FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Basescited by 10
  6. 2025Hierarchical Flow Diffusion for Efficient Frame Interpolationcited by 7
  7. 2024Dynamic Neural Radiance Field From Defocused Monocular Videocited by 6
  8. 2021Sensor-Guided Optical Flowcited by 4
  9. 2021Joint Detection of Motion Boundaries and Occlusionscited by 4
  10. 2023Point-and-Shoot All-in-Focus Photo Synthesis from Smartphone Camera Paircited by 4
  11. 2025CineMyoPS: Segmenting Myocardial Pathologies from Cine Cardiac MRcited by 3
  12. 2024Egocentric Vision Language Planningcited by 2
  13. 2025ProbDiffFlow: An Efficient Learning-Free Framework for Probabilistic Single-Image Optical Flow Estimationcited by 2
  14. 2021Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fieldscited by 1
  15. 2026Triangular Consistency as a Universal Constraint for Learning Optical Flowcited by 1
  16. 2022Learning Omnidirectional Flow in 360-degree Video via Siamese Representationcited by 0
  17. 2022A Compacted Structure for Cross-domain learning on Monocular Depth and Flow Estimationcited by 0
  18. 2023Optical Flow Estimation in 360^circ Videos: Dataset, Model and Applicationcited by 0
  19. 2023Skin the sheep not only once: Reusing Various Depth Datasets to Drive the Learning of Optical Flowcited by 0
  20. 2024Multi-view Disparity Estimation Using a Novel Gradient Consistency Modelcited by 0
  21. 2024HMAFlow: Learning More Accurate Optical Flow via Hierarchical Motion Field Alignmentcited by 0
  22. 2025Dual-Camera All-in-Focus Neural Radiance Fieldscited by 0