Share Email Print
cover

Proceedings Paper

Learning the missing values in depth maps
Author(s): Xuanwu Yin; Guijin Wang; Chun Zhang; Qingmin Liao
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, we consider the task of hole filling in depth maps, with the help of an associated color image. We take a supervised learning approach to solve this problem. The model is learnt from the training set, which contain pixels that have depth values. Then we apply supervised learning to predict the depth values in the holes. Our model uses a regional Markov Random Field (MRF) that incorporates multiscale absolute and relative features (computed from the color image), and models depths not only at individual points but also between adjacent points. The experiments show that the proposed approach is able to recover fairly accurate depth values and achieve a high quality depth map.

Paper Details

Date Published: 19 December 2013
PDF: 6 pages
Proc. SPIE 9045, 2013 International Conference on Optical Instruments and Technology: Optoelectronic Imaging and Processing Technology, 904508 (19 December 2013); doi: 10.1117/12.2035370
Show Author Affiliations
Xuanwu Yin, Tsinghua Univ. (China)
Guijin Wang, Tsinghua Univ. (China)
Chun Zhang, Tsinghua Univ. (China)
Qingmin Liao, Tsinghua Univ. (China)


Published in SPIE Proceedings Vol. 9045:
2013 International Conference on Optical Instruments and Technology: Optoelectronic Imaging and Processing Technology
Xinggang Lin; Jesse Zheng, Editor(s)

© SPIE. Terms of Use
Back to Top