Share Email Print
cover

Proceedings Paper

Depth image super-resolution via semi self-taught learning framework
Author(s): Furong Zhao; Zhiguo Cao; Yang Xiao; Xiaodi Zhang; Ke Xian; Ruibo Li
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Depth images have recently attracted much attention in computer vision and high-quality 3D content for 3DTV and 3D movies. In this paper, we present a new semi self-taught learning application framework for enhancing resolution of depth maps without making use of ancillary color images data at the target resolution, or multiple aligned depth maps. Our framework consists of cascade random forests reaching from coarse to fine results. We learn the surface information and structure transformations both from a small high-quality depth exemplars and the input depth map itself across different scales. Considering that edge plays an important role in depth map quality, we optimize an effective regularized objective that calculates on output image space and input edge space in random forests. Experiments show the effectiveness and superiority of our method against other techniques with or without applying aligned RGB information

Paper Details

Date Published: 26 June 2017
PDF: 11 pages
Proc. SPIE 10332, Videometrics, Range Imaging, and Applications XIV, 103320R (26 June 2017); doi: 10.1117/12.2270079
Show Author Affiliations
Furong Zhao, Huazhong Univ. of Science and Technology (China)
Zhiguo Cao, Huazhong Univ. of Science and Technology (China)
Yang Xiao, Huazhong Univ. of Science and Technology (China)
Xiaodi Zhang, Huazhong Univ. of Science and Technology (China)
Ke Xian, Huazhong Univ. of Science and Technology (China)
Ruibo Li, Huazhong Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 10332:
Videometrics, Range Imaging, and Applications XIV
Fabio Remondino; Mark R. Shortis, Editor(s)

© SPIE. Terms of Use
Back to Top