Bidirectional Attention Network for Monocular Depth Estimation

1 code implementation • 1 Sep 2020 • Shubhra Aich, Jean Marie Uwabeza Vianney, Md Amirul Islam, Mannat Kaur, Bingbing Liu

In this paper, we propose a Bidirectional Attention Network (BANet), an end-to-end framework for monocular depth estimation (MDE) that addresses the limitation of effectively integrating local and global information in convolutional neural networks.

Machine Translation Monocular Depth Estimation +1