FADNet: A Fast and Accurate Network for Disparity Estimation

Qiang Wang, Shaohuai Shi, Shizhen Zheng, Kaiyong Zhao*, Xiaowen Chu*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

54 Citations (Scopus)


Deep neural networks (DNNs) have achieved great success in the area of computer vision. The disparity estimation problem tends to be addressed by DNNs which achieve much better prediction accuracy in stereo matching than traditional hand-crafted feature based methods. On one hand, however, the designed DNNs require significant memory and computation resources to accurately predict the disparity, especially for those 3D convolution based networks, which makes it difficult for deployment in real-time applications. On the other hand, existing computation-efficient networks lack expression capability in large-scale datasets so that they cannot make an accurate prediction in many scenarios. To this end, we propose an efficient and accurate deep network for disparity estimation named FADNet with three main features: 1) It exploits efficient 2D based correlation layers with stacked blocks to preserve fast computation; 2) It combines the residual structures to make the deeper model easier to learn; 3) It contains multi-scale predictions so as to exploit a multi-scale weight scheduling training technique to improve the accuracy. We conduct experiments to demonstrate the effectiveness of FADNet on two popular datasets, Scene Flow and KITTI 2015. Experimental results show that FADNet achieves state-of-the-art prediction accuracy, and runs at a significant order of magnitude faster speed than existing 3D models. The codes of FADNet are available at https://github.com/HKBU-HPML/FADNet.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Robotics and Automation, ICRA 2020
Number of pages7
ISBN (Electronic)9781728173955, 9781728173948
ISBN (Print)9781728173962
Publication statusPublished - May 2020
Event2020 IEEE International Conference on Robotics and Automation, ICRA 2020 - Paris, France
Duration: 31 May 202031 Aug 2020

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729


Conference2020 IEEE International Conference on Robotics and Automation, ICRA 2020

Scopus Subject Areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering


Dive into the research topics of 'FADNet: A Fast and Accurate Network for Disparity Estimation'. Together they form a unique fingerprint.

Cite this