# FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network

arXiv: https://arxiv.org/abs/2006.12263 · HTML: https://mlsanity.com/paper/2006.12263/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2020.

## Built on by (most cited first, 7 of 7)

- [FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation](https://mlsanity.com/paper/2103.04524/) (2021)
- [MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation](https://mlsanity.com/paper/2211.06018/) (2022)
- [Dynamic Frame Interpolation in Wavelet Domain](https://mlsanity.com/paper/2309.03508/) (2023)
- [OAS-Net: Occlusion Aware Sampling Network for Accurate Optical Flow](https://mlsanity.com/paper/2102.00364/) (2021)
- [Unsupervised Motion Representation Enhanced Network for Action Recognition](https://mlsanity.com/paper/2103.03465/) (2021)
- [SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations](https://mlsanity.com/paper/2404.08135/) (2024)
- [CompactFlowNet: Efficient Real-time Optical Flow Estimation on Mobile Devices](https://mlsanity.com/paper/2412.13273/) (2024)

## Abstract (arXiv)

Significant progress has been made for estimating optical flow using deep neural networks. Advanced deep models achieve accurate flow estimation often with a considerable computation complexity and time-consuming training processes. In this work, we present a lightweight yet effective model for real-time optical flow estimation, termed FDFlowNet (fast deep flownet). We achieve better or similar accuracy on the challenging KITTI and Sintel benchmarks while being about 2 times faster than PWC-Net. This is achieved by a carefully-designed structure and newly proposed components. We first introduce an U-shape network for constructing multi-scale feature which benefits upper levels with global receptive field compared with pyramid network. In each scale, a partial fully connected structure with dilated convolution is proposed for flow estimation that obtains a good balance among speed, accuracy and number of parameters compared with sequential connected and dense connected structures. Experiments demonstrate that our model achieves state-of-the-art performance while being fast and lightweight.