# Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM

## TL;DR

This paper introduces PCLNet, an unsupervised pyramid ConvLSTM framework for optical flow estimation that is flexible, accurate, and easily integrable into various CNN-based applications, with verified effectiveness in multiple tasks.

## Contribution

The paper proposes a novel unsupervised optical flow framework using pyramid ConvLSTM that decouples motion learning from flow representation, improving accuracy and flexibility over existing methods.

## Key findings

- Effective and accurate optical flow estimation demonstrated.
- Comparable performance achieved in action recognition tasks.
- Framework easily integrates with generic CNN architectures.

## Abstract

Most of current Convolution Neural Network (CNN) based methods for optical flow estimation focus on learning optical flow on synthetic datasets with groundtruth, which is not practical. In this paper, we propose an unsupervised optical flow estimation framework named PCLNet. It uses pyramid Convolution LSTM (ConvLSTM) with the constraint of adjacent frame reconstruction, which allows flexibly estimating multi-frame optical flows from any video clip. Besides, by decoupling motion feature learning and optical flow representation, our method avoids complex short-cut connections used in existing frameworks while improving accuracy of optical flow estimation. Moreover, different from those methods using specialized CNN architectures for capturing motion, our framework directly learns optical flow from the features of generic CNNs and thus can be easily embedded in any CNN based frameworks for other tasks. Extensive experiments have verified that our method not only estimates optical flow effectively and accurately, but also obtains comparable performance on action recognition.