Sensors 2018, 18(3), 764; https://doi.org/10.3390/s18030764
Three-Dimensional Reconstruction from Single Image Base on Combination of CNN and Multi-Spectral Photometric Stereo
College of Information Science and Engineering, Ocean University of China, Qingdao 266100, China
†
These authors contributed equally to this work and should be considered co-first authors.
*
Author to whom correspondence should be addressed.
Received: 17 December 2017 / Revised: 14 February 2018 / Accepted: 14 February 2018 / Published: 2 March 2018
(This article belongs to the Special Issue Sensing, Data Analysis and Platforms for Ubiquitous Intelligence)
Abstract
Multi-spectral photometric stereo can recover pixel-wise surface normal from a single RGB image. The difficulty lies in that the intensity in each channel is the tangle of illumination, albedo and camera response; thus, an initial estimate of the normal is required in optimization-based solutions. In this paper, we propose to make a rough depth estimation using the deep convolutional neural network (CNN) instead of using depth sensors or binocular stereo devices. Since high-resolution ground-truth data is expensive to obtain, we designed a network and trained it with rendered images of synthetic 3D objects. We use the model to predict initial normal of real-world objects and iteratively optimize the fine-scale geometry in the multi-spectral photometric stereo framework. The experimental results illustrate the improvement of the proposed method compared with existing methods. View Full-Text
Figure 1
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 (CC BY 4.0).
Share & Cite This Article
MDPI and ACS Style
Lu, L.; Qi, L.; Luo, Y.; Jiao, H.; Dong, J. Three-Dimensional Reconstruction from Single Image Base on Combination of CNN and Multi-Spectral Photometric Stereo. Sensors 2018, 18, 764.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.