| |
The performance of depth reconstruction in binocular stereo relies on how adequate the predefined baseline for a target scene is. Long-baseline stereo is capable of discriminating depth better than the short one, but it often suffers from spatial artifacts. Short-baseline stereo can provide a more elaborate depth map with less artifacts, while its depth resolution tends to be biased or coarse due to the short disparity. In this paper, we first propose a novel optical design of heterogeneous stereo fusion on a binocular imaging system with a refractive medium, where the binocular stereo part operates as long-baseline stereo; the refractive stereo module functions as short-baseline stereo. We then introduce a stereo fusion workflow that combines the refractive and binocular stereo algorithms to estimate fine depth information through this fusion design. The quantitative and qualitative results validate the performance of our stereo fusion system in measuring depth, compared with traditional homogeneous stereo approaches. |
| |
@ InProceedings{BaekKim:ACCV:2014,
author = {Seung-Hwan Baek and Min H. Kim},
title = {Stereo Fusion using a Refractive Medium on a Binocular Base},
booktitle = {Proc. Asian Conference on Computer Vision (ACCV 2014)},
year = {2015},
pages = {503--518},
publisher = {Springer},
volume = {9004},
series = "Lecture Notes in Computer Science (LNCS)",
address = {Singapore, Singapore},
}
|
