FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation

@article{Kong2021FastFlowNetAL,
  title={FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation},
  author={Lingtong Kong and Chunhua Shen and Jie Yang},
  journal={2021 IEEE International Conference on Robotics and Automation (ICRA)},
  year={2021},
  pages={10310-10316}
}
Dense optical flow estimation plays a key role in many robotic vision tasks. In the past few years, with the advent of deep learning, we have witnessed great progress in optical flow estimation. However, current networks often consist of a large number of parameters and require heavy computation costs, largely hindering its application on low power-consumption devices such as mobile phones. In this paper, we tackle this challenge and design a lightweight model for fast and accurate optical flow… 
View on IEEE
arxiv.org
3 Citations
Background Citations
3
Methods Citations
1

Figures and Tables from this paper

3 Citations

IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation
TLDR
An efficient encoder-decoder based network, termed IFRNet, for fast intermediate frame synthesizing, which first extracts pyramid features from given inputs, and then refines the bilateral intermediate flow fields together with a powerful intermediate feature until generating the desired output.
Optical Flow Based Motion Detection for Autonomous Driving
TLDR
Aiming at distant vehicles, a neural network model is trained to classify the motion status using optical flow field information as the input, showing that the idea is viable and promising.
Contextual Detection of Pedestrians and Vehicles in Orthophotography by Fusion of Deep Learning Algorithms
TLDR
The presented results show that the method allows one to detect road users, identify the surfaces on which they move, quantify their apparent velocity, and estimate their actual velocity.

References

SHOWING 1-10 OF 32 REFERENCES
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
TLDR
This work introduces two simple global hyper-parameters that efficiently trade off between latency and accuracy and demonstrates the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.
Object scene flow for autonomous vehicles
TLDR
A novel model and dataset for 3D scene flow estimation with an application to autonomous driving by representing each element in the scene by its rigid motion parameters and each superpixel by a 3D plane as well as an index to the corresponding object.
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
TLDR
This paper presents an alternative network that attains performance on par with FlowNet2 on the challenging Sintel final pass and KITTI benchmarks, while being 30 times smaller in the model size and 1.36 times faster in the running speed.
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
TLDR
An extremely computation-efficient CNN architecture named ShuffleNet is introduced, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs), to greatly reduce computation cost while maintaining accuracy.
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
  • N. Mayer, Eddy Ilg, T. Brox
  • Computer Science
    2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
TLDR
This paper proposes three synthetic stereo video datasets with sufficient realism, variation, and size to successfully train large networks and presents a convolutional network for real-time disparity estimation that provides state-of-the-art results.
FlowNet: Learning Optical Flow with Convolutional Networks
TLDR
This paper constructs CNNs which are capable of solving the optical flow estimation problem as a supervised learning task, and proposes and compares two architectures: a generic architecture and another one including a layer that correlates feature vectors at different image locations.
Improving Optical Flow on a Pyramid Level
TLDR
This work improves the cost volume construction process within an individual pyramid level, and improves the gradient flow across pyramid levels, and introduces a distillation concept to counteract the issue of catastrophic forgetting and thus preserving knowledge over models sequentially trained on multiple datasets.
Fdflownet: Fast Optical Flow Estimation Using A Deep Lightweight Network
TLDR
This work presents a lightweight yet effective model for real-time optical flow estimation, termed FDFlowNet (fast deep flownet), which achieves better or similar accuracy on the challenging KITTI and Sintel benchmarks while being about 2 times faster than PWC-Net.
Unsupervised Motion Representation Enhanced Network for Action Recognition
TLDR
UF-TSN is proposed, a novel end-to-end action recognition approach enhanced with an embedded lightweight unsupervised optical flow estimator that achieves better accuracy while maintaining efficiency, which is competitive with some supervised or more complicated approaches.
Fine-Grained Motion Representation For Template-Free Visual Tracking
TLDR
The finer-grained motion estimation is explored to improve the accuracy of the template-free model and is the first work to model the displacement, scaling and rotation in a unified theory with the optical flow.
...
...