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

arXiv: https://arxiv.org/abs/1604.03513 · HTML: https://mlsanity.com/paper/1604.03513/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2016.

## Built on by (most cited first, 30 of 34)

- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow](https://mlsanity.com/paper/2405.14793/) (2024)
- [Track to Detect and Segment: An Online Multi-Object Tracker](https://mlsanity.com/paper/2103.08808/) (2021)
- [SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping](https://mlsanity.com/paper/2105.07014/) (2021)
- [Global Matching with Overlapping Attention for Optical Flow Estimation](https://mlsanity.com/paper/2203.11335/) (2022)
- [Deep Equilibrium Optical Flow Estimation](https://mlsanity.com/paper/2204.08442/) (2022)
- [SKFlow: Learning Optical Flow with Super Kernels](https://mlsanity.com/paper/2205.14623/) (2022)
- [High-Resolution Optical Flow from 1D Attention and Correlation](https://mlsanity.com/paper/2104.13918/) (2021)
- [Learning Optical Flow from a Few Matches](https://mlsanity.com/paper/2104.02166/) (2021)
- [WAFT: Warping-Alone Field Transforms for Optical Flow](https://mlsanity.com/paper/2506.21526/) (2025)
- [GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects](https://mlsanity.com/paper/2403.11510/) (2024)
- [Learning optical flow from still images](https://mlsanity.com/paper/2104.03965/) (2021)
- [DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks](https://mlsanity.com/paper/2304.00571/) (2023)
- [Shape-Constraint Recurrent Flow for 6D Object Pose Estimation](https://mlsanity.com/paper/2306.13266/) (2023)
- [SAMConvex: Fast Discrete Optimization for CT Registration using Self-supervised Anatomical Embedding and Correlation Pyramid](https://mlsanity.com/paper/2307.09727/) (2023)
- [Match Cutting: Finding Cuts with Smooth Visual Transitions](https://mlsanity.com/paper/2210.05766/) (2022)
- [FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases](https://mlsanity.com/paper/2509.05297/) (2025)
- [Hierarchical Flow Diffusion for Efficient Frame Interpolation](https://mlsanity.com/paper/2504.00380/) (2025)
- [Dynamic Neural Radiance Field From Defocused Monocular Video](https://mlsanity.com/paper/2407.05586/) (2024)
- [Sensor-Guided Optical Flow](https://mlsanity.com/paper/2109.15321/) (2021)
- [Joint Detection of Motion Boundaries and Occlusions](https://mlsanity.com/paper/2111.01261/) (2021)
- [Point-and-Shoot All-in-Focus Photo Synthesis from Smartphone Camera Pair](https://mlsanity.com/paper/2304.04917/) (2023)
- [CineMyoPS: Segmenting Myocardial Pathologies from Cine Cardiac MR](https://mlsanity.com/paper/2507.02289/) (2025)
- [Egocentric Vision Language Planning](https://mlsanity.com/paper/2408.05802/) (2024)
- [ProbDiffFlow: An Efficient Learning-Free Framework for Probabilistic Single-Image Optical Flow Estimation](https://mlsanity.com/paper/2503.12348/) (2025)
- [Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields](https://mlsanity.com/paper/2107.06028/) (2021)
- [Triangular Consistency as a Universal Constraint for Learning Optical Flow](https://mlsanity.com/paper/2606.19938/) (2026)
- [Learning Omnidirectional Flow in 360-degree Video via Siamese Representation](https://mlsanity.com/paper/2208.03620/) (2022)
- [A Compacted Structure for Cross-domain learning on Monocular Depth and Flow Estimation](https://mlsanity.com/paper/2208.11993/) (2022)
- [Optical Flow Estimation in 360^circ Videos: Dataset, Model and Application](https://mlsanity.com/paper/2301.11880/) (2023)

## 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.