Transfer2Depth: Dual Attention Network with Transfer Learning for Monocular Depth Estimation

Chia Hung Yeh, Yao Pao Huang, Chih Yang Lin*, Chuan Yu Chang

*此作品的通信作者

研究成果: 雜誌貢獻期刊論文同行評審

1 引文 斯高帕斯(Scopus)

摘要

Monocular depth estimation poses a fundamental problem in many tasks. Although recent convolutional neural network-based methods can achieve high accuracy with very deep networks and complex architectures to exploit different cues and features, doing so not only increases the vulnerability of the model, but also increases the difficulty of convergence. Moreover, recent depth estimation methods for indoor environments are impractical for outdoor environments. In this work, we aim to develop a simple deep network structure to improve model effectiveness for depth estimation. We apply a dual attention module that can be inserted into any type of network to improve the power of representation, and additionally propose a training strategy which combines transfer learning and ordinal regression to improve training convergence. Even with a simple end-to-end encoder-decoder type of network architecture, we are able to achieve state-of-the-art performance on two of the biggest datasets for indoor and outdoor depth estimation: NYU Depth v2 and KITTI.

原文英語
文章編號9087902
頁(從 - 到)86081-86090
頁數10
期刊IEEE Access
8
DOIs
出版狀態已發佈 - 2020

ASJC Scopus subject areas

  • 電腦科學(全部)
  • 材料科學(全部)
  • 工程 (全部)

指紋

深入研究「Transfer2Depth: Dual Attention Network with Transfer Learning for Monocular Depth Estimation」主題。共同形成了獨特的指紋。

引用此