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

TL;DR

This paper introduces a global optimization method for optical flow estimation that efficiently searches over regular grid mappings, achieving state-of-the-art results without descriptor matching.

Contribution

It proposes a novel global optimization framework over regular grids that reduces computational complexity and improves optical flow estimation accuracy.

Findings

Reduced optimization complexity from quadratic to linear

Achieved state-of-the-art performance on benchmarks

No descriptor matching required

Abstract

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.