8 February 2017 Surface height map estimation from a single image using convolutional neural networks
Author Affiliations +
Proceedings Volume 10225, Eighth International Conference on Graphic and Image Processing (ICGIP 2016); 1022524 (2017) https://doi.org/10.1117/12.2266479
Event: Eighth International Conference on Graphic and Image Processing, 2016, Tokyo, Japan
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.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiaowei Zhou, Xiaowei Zhou, Guoqiang Zhong, Guoqiang Zhong, Lin Qi, Lin Qi, Junyu Dong, Junyu Dong, Tuan D. Pham, Tuan D. Pham, Jianzhou Mao, Jianzhou Mao, } "Surface height map estimation from a single image using convolutional neural networks", Proc. SPIE 10225, Eighth International Conference on Graphic and Image Processing (ICGIP 2016), 1022524 (8 February 2017); doi: 10.1117/12.2266479; https://doi.org/10.1117/12.2266479
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

Image-based air target identification
Proceedings of SPIE (September 21 1994)
Visual data exploration using Legendre wavelets
Proceedings of SPIE (March 08 1996)
Texture discrimination through fractal geometry
Proceedings of SPIE (June 14 1996)
Color Texture Analysis And Synthesis Using Gibbs Random Fields
Proceedings of SPIE (September 05 1989)

Back to Top