Share Email Print
cover

Proceedings Paper

Surface height map estimation from a single image using convolutional neural networks
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Surface height map estimation is an important task in high-resolution 3D reconstruction. This task differs from general scene depth estimation in the fact that surface height maps contain more high frequency information or fine details. Existing methods based on radar or other equipments can be used for large-scale scene depth recovery, but might fail in small-scale surface height map estimation. Although some methods are available for surface height reconstruction based on multiple images, e.g. photometric stereo, height map estimation directly from a single image is still a challenging issue. In this paper, we present a novel method based on convolutional neural networks (CNNs) for estimating the height map from a single image, without any equipments or extra prior knowledge of the image contents. Experimental results based on procedural and real texture datasets show the proposed algorithm is effective and reliable.

Paper Details

Date Published: 8 February 2017
PDF: 6 pages
Proc. SPIE 10225, Eighth International Conference on Graphic and Image Processing (ICGIP 2016), 1022524 (8 February 2017); doi: 10.1117/12.2266479
Show Author Affiliations
Xiaowei Zhou, Ocean Univ. of China (China)
Guoqiang Zhong, Ocean Univ. of China (China)
Lin Qi, Ocean Univ. of China (China)
Junyu Dong, Ocean Univ. of China (China)
Tuan D. Pham, Linkoping Univ. (China)
Jianzhou Mao, Macau Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 10225:
Eighth International Conference on Graphic and Image Processing (ICGIP 2016)
Yulin Wang; Tuan D. Pham; Vit Vozenilek; David Zhang; Yi Xie, Editor(s)

© SPIE. Terms of Use
Back to Top