Bidirectional Attention Network for Monocular Depth Estimation

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. The structure of this mechanism derives from a strong conceptual foundation of neural machine translation, and presents a light-weight mechanism for adaptive control of computation similar to the dynamic nature of recurrent neural networks. We introduce bidirectional attention modules that utilize the feed-forward feature maps and incorporate the global context to filter out ambiguity. Extensive experiments reveal the high degree of capability of this bidirectional attention model over feed-forward baselines and other state-of-the-art methods for monocular depth estimation on two challenging datasets - KITTI and DIODE. We show that our proposed approach either outperforms or performs at least on a par with the state-of-the-art monocular depth estimation methods with less memory and computational complexity.

Authors

• Shubhra Aich
• Jean Marie Uwabeza Vianney
• Md. Amirul Islam
• Mannat Kaur
• Bingbing Liu

Keywords

• Recurrent neural networks
• Conferences
• Computational modeling
• Memory management
• Estimation
• Machine translation
• Convolutional neural networks
• Depth Estimation
• Bidirectional Network
• Monocular Depth Estimation
• Bidirectional Attention
• Convolutional Network
• Convolutional Neural Network
• Feature Maps
• Global Context
• Global Information
• Challenging Dataset
• Neural Machine Translation
• Spatial Resolution
• Deep Learning
• Attention Mechanism
• Ordinal Regression
• Depth Map
• Spatial Attention
• Skip Connections
• Words In Sentences
• Standard Datasets
• Bidirectional Recurrent Neural Network
• Markov Random Field
• Depth Prediction