Share Email Print

Proceedings Paper

Joint upsampling and noise reduction for real-time depth map enhancement
Author(s): Kazuki Matsumoto; Chiyoung Song; Francois de Sorbier; Hideo Saito
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

An efficient system that upsamples depth map captured by Microsoft Kinect while jointly reducing the effect of noise is presented. The upsampling is carried by detecting and exploiting the piecewise locally planar structures of the downsampled depth map, based on corresponding high-resolution RGB image. The amount of noise is reduced by accumulating the downsampled data simultaneously. By benefiting from massively parallel computing capability of modern commodity GPUs, the system is able to maintain high frame rate. Our system is observed to produce the upsampled depth map that is very close to the original depth map both visually and mathematically.

Paper Details

Date Published: 6 March 2014
PDF: 11 pages
Proc. SPIE 9011, Stereoscopic Displays and Applications XXV, 901120 (6 March 2014);
Show Author Affiliations
Kazuki Matsumoto, Keio Univ. (Japan)
Chiyoung Song, Keio Univ. (Japan)
Francois de Sorbier, Keio Univ. (Japan)
Hideo Saito, Keio Univ. (Japan)

Published in SPIE Proceedings Vol. 9011:
Stereoscopic Displays and Applications XXV
Andrew J. Woods; Nicolas S. Holliman; Gregg E. Favalora, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?