Related projects

Proj – 04 – transformer

sym

MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer (paper) Chaoqiang Zhao, Youmin Zhang, Matteo Poggi, Fabio Tosi, Xianda Guo,Zheng Zhu, Guan Huang, Yang Tang, Stefano Mattoccia

International Conference on 3D Vision, 2022

  • Improving the self-supervised monocular depth estimation by using a transformer.

Proj – 03 – domain adaptation

sym

Unsupervised Monocular Depth Estimation in Highly Complex Environments (paper) Chaoqiang Zhao, Yang Tang, Qiyu Sun

Accepted by IEEE Transactions on Emerging Topics in Computational Intelligence, 2022

  • Using domain adaptation to tackle the problem of unsupervised monocular depth estimation in complex environments, like night and rainy night.

Proj – 02 – visual odometry

sym

Deep direct visual odometry (paper) Chaoqiang Zhao,Yang Tang, Qiyu Sun, Athanasios V Vasilakos

IEEE Transactions on Intelligent Transportation Systems, 2021

  • Introducing deep neural pose estimation into traditional DSO framework for robust initialization and accurate tracking.

Proj – 01 – adversarial learning

sym

Masked GAN for unsupervised depth and pose prediction with scale consistency (paper) Chaoqiang Zhao, Gary G Yen, Qiyu Sun, Chongzhen Zhang, Yang Tang

IEEE Transactions on Neural Networks and Learning Systems, 2020

  • Improve the adversarial loss used in unsupervised monocular depth estimation framework.