6 March 2014 Joint upsampling and noise reduction for real-time depth map enhancement
Author Affiliations +
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.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kazuki Matsumoto, Kazuki Matsumoto, Chiyoung Song, Chiyoung Song, Francois de Sorbier, Francois de Sorbier, Hideo Saito, Hideo Saito, "Joint upsampling and noise reduction for real-time depth map enhancement", Proc. SPIE 9011, Stereoscopic Displays and Applications XXV, 901120 (6 March 2014); doi: 10.1117/12.2039190; https://doi.org/10.1117/12.2039190

Back to Top