Reconstruction of high-resolution Depth Map using Sparse Linear Model

DOI

10.2991/isrme-15.2015.65How to use a DOI?

Keywords

Depth Image; Sparse Representation

Abstract

In this paper, we propose a method that constructs a high-resolution depth image with high quality from a low-resolution depth image that is noisy and contains holes. We believe that the high-resolution depth map is generated by sparse linear combination of atoms from an over-complete dictionary, and the low-resolution depth map are the samples from the high-resolution depth map. Under Bayesian framework, we find the optimal sparse coefficient vector that represents the high-resolution map best. Comprehensive quantitative comparisons show that our method outperforms existing approaches when applied on Middlebury dataset, and qualitative comparison on real scenes indicates that our algorithm performs best.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Hanqi Fan
AU  - Dexing Kong
AU  - Jinhong Li
PY  - 2015/04
DA  - 2015/04
TI  - Reconstruction of high-resolution Depth Map using Sparse Linear Model
BT  - Proceedings of the 2015 International Conference on Intelligent Systems Research and Mechatronics Engineering
PB  - Atlantis Press
SP  - 283
EP  - 292
SN  - 1951-6851
UR  - https://doi.org/10.2991/isrme-15.2015.65
DO  - 10.2991/isrme-15.2015.65
ID  - Fan2015/04
ER  -