What Matters in Unsupervised Optical Flow

TL;DR

This paper systematically analyzes key components of unsupervised optical flow, introduces novel improvements, and presents a new method that outperforms previous unsupervised approaches and rivals supervised models on KITTI 2015.

Contribution

The paper identifies effective components and proposes novel improvements, resulting in an unsupervised optical flow method that matches supervised performance with simpler design.

Findings

Outperforms previous unsupervised state-of-the-art methods.

Achieves performance comparable to supervised FlowNet2 on KITTI 2015.

Introduces effective techniques like cost volume normalization and self-supervision.

Abstract

We systematically compare and analyze a set of key components in unsupervised optical flow to identify which photometric loss, occlusion handling, and smoothness regularization is most effective. Alongside this investigation we construct a number of novel improvements to unsupervised flow models, such as cost volume normalization, stopping the gradient at the occlusion mask, encouraging smoothness before upsampling the flow field, and continual self-supervision with image resizing. By combining the results of our investigation with our improved model components, we are able to present a new unsupervised flow technique that significantly outperforms the previous unsupervised state-of-the-art and performs on par with supervised FlowNet2 on the KITTI 2015 dataset, while also being significantly simpler than related approaches.