HMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving Objects
This work is significant for improving optical flow estimation, particularly for applications involving small and fast-moving objects, which are often missed by existing coarse-to-fine methods.
This paper addresses the challenge of optical flow networks failing to capture small and fast-moving objects due to limitations in the coarse-to-fine warping strategy. The authors propose HMFlow, a hybrid network that integrates a lightweight Global Matching Component (GMC) to guide the network in discovering these hard-to-match objects, while maintaining high accuracy and small model size.
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.