Guided Optical Flow Learning

TL;DR

This paper introduces a guided unsupervised learning framework for optical flow estimation that leverages proxy ground truth data from classical methods, achieving real-time performance and competitive accuracy.

Contribution

The novel framework combines proxy ground truth guidance with unsupervised refinement, improving optical flow estimation without requiring true ground truth data.

Findings

Achieves state-of-the-art results on benchmark datasets

Operates in real time with competitive accuracy

Does not require true ground truth optical flow data

Abstract

We study the unsupervised learning of CNNs for optical flow estimation using proxy ground truth data. Supervised CNNs, due to their immense learning capacity, have shown superior performance on a range of computer vision problems including optical flow prediction. They however require the ground truth flow which is usually not accessible except on limited synthetic data. Without the guidance of ground truth optical flow, unsupervised CNNs often perform worse as they are naturally ill-conditioned. We therefore propose a novel framework in which proxy ground truth data generated from classical approaches is used to guide the CNN learning. The models are further refined in an unsupervised fashion using an image reconstruction loss. Our guided learning approach is competitive with or superior to state-of-the-art approaches on three standard benchmark datasets yet is completely unsupervised and can run in real time.