# Guided Optical Flow Learning

arXiv: https://arxiv.org/abs/1702.02295 · HTML: https://mlsanity.com/paper/1702.02295/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2017.

## Built on by (most cited first, 1 of 1)

- [Self-SuperFlow: Self-supervised Scene Flow Prediction in Stereo Sequences](https://mlsanity.com/paper/2206.15296/) (2022)

## Abstract (arXiv)

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.