Bidirectional Attention Network for Monocular Depth Estimation

2020/09/01 by Shubhra Aich, Aich, Shubhra, Jean Marie Uwabeza Vianney +7 · 1 citation
Computer Science · Engineering · #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #Optical measurement and interference techniques #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2009.00743

openalex publication_date 2020/09/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• ImageNet classification with deep convolutional neural networks
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Fully Convolutional Networks for Semantic Segmentation
• RefinedMPL: Refined Monocular PseudoLiDAR for 3D Object Detection in Autonomous Driving
• ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

Cited by

• Region-aware Depth Scale Adaptation with Sparse Measurements

Related

• Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
• Self-supervised Monocular Depth Estimation with Large Kernel Attention
• A Weakly-Supervised Depth Estimation Network Using Attention Mechanism
• Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation
• Depth Monocular Estimation with Attention-based Encoder-Decoder Network from Single Image