Superb Monocular Depth Estimation Based on Transfer Learning and Surface Normal Guidance
1
Department of Mechanical Engineering and Automation, School of Mechanical and Aerospace Engineering, Jilin University, Changchun 130022, China
2
Research Center for Space Optical Engineering, Harbin Institute of Technology, P.O. Box 307, Harbin 150001, China
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(17), 4856; https://doi.org/10.3390/s20174856
Received: 3 August 2020
/
Revised: 24 August 2020
/
Accepted: 25 August 2020
/
Published: 27 August 2020
(This article belongs to the Section Intelligent Sensors)
Accurately sensing the surrounding 3D scene is indispensable for drones or robots to execute path planning and navigation. In this paper, a novel monocular depth estimation method was proposed that primarily utilizes a lighter-weight Convolutional Neural Network (CNN) structure for coarse depth prediction and then refines the coarse depth images by combining surface normal guidance. Specifically, the coarse depth prediction network is designed as pre-trained encoder–decoder architecture for describing the 3D structure. When it comes to surface normal estimation, the deep learning network was designed as a two-stream encoder–decoder structure, which hierarchically merges red-green-blue-depth (RGB-D) images for capturing more accurate geometric boundaries. Relying on fewer network parameters and simpler learning structure, better detailed depth maps are produced than the existing states. Moreover, 3D point cloud maps reconstructed from depth prediction images confirm that our framework can be conveniently adopted as components of a monocular simultaneous localization and mapping (SLAM) paradigm.
View Full-Text
Keywords:
SLAM; SFM; supervised deep learning; multi-task learning; transfer learning; monocular depth estimation; surface normal estimation
▼
Show Figures
Graphical abstract
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
MDPI and ACS Style
Huang, K.; Qu, X.; Chen, S.; Chen, Z.; Zhang, W.; Qi, H.; Zhao, F. Superb Monocular Depth Estimation Based on Transfer Learning and Surface Normal Guidance. Sensors 2020, 20, 4856. https://doi.org/10.3390/s20174856
AMA Style
Huang K, Qu X, Chen S, Chen Z, Zhang W, Qi H, Zhao F. Superb Monocular Depth Estimation Based on Transfer Learning and Surface Normal Guidance. Sensors. 2020; 20(17):4856. https://doi.org/10.3390/s20174856
Chicago/Turabian StyleHuang, Kang, Xingtian Qu, Shouqian Chen, Zhen Chen, Wang Zhang, Haogang Qi, and Fengshang Zhao. 2020. "Superb Monocular Depth Estimation Based on Transfer Learning and Surface Normal Guidance" Sensors 20, no. 17: 4856. https://doi.org/10.3390/s20174856
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
