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

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

研究成果: 雜誌貢獻期刊論文同行評審

6 引文 斯高帕斯(Scopus)


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.

頁(從 - 到)86081-86090
期刊IEEE Access
出版狀態已出版 - 2020


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。