HMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving Objects

TL;DR

HMFlow introduces a hybrid optical flow network with a global matching component to improve detection of small and fast-moving objects, outperforming traditional coarse-to-fine methods especially in challenging regions.

Contribution

The paper presents a novel hybrid optical flow network integrating global matching for better small and fast object detection, along with a new dataset for evaluation.

Findings

Enhanced accuracy on small and fast-moving objects

Maintains small model size and high efficiency

Outperforms existing coarse-to-fine methods in experiments

Abstract

In optical flow estimation task, coarse-to-fine (C2F) warping strategy is widely used to deal with the large displacement problem and provides efficiency and speed. However, limited by the small search range between the first images and warped second images, current coarse-to-fine optical flow networks fail to capture small and fast-moving objects which disappear at coarse resolution levels. To address this problem, we introduce a lightweight but effective Global Matching Component (GMC) to grab global matching features. We propose a new Hybrid Matching Optical Flow Network (HMFlow) by integrating GMC into existing coarse-to-fine networks seamlessly. Besides keeping in high accuracy and small model size, our proposed HMFlow can apply global matching features to guide the network to discover the small and fast-moving objects mismatched by local matching features. We also build a new dataset, named Small and Fast-Moving Chairs (SFChairs), for evaluation. The experimental results show that our proposed network achieves considerable performance, especially at regions with small and fast-moving objects.