Confidence-based refinement of corrupted depth maps

Confidence-based refinement of corrupted depth maps
复制标题

DOI:
--
复制
发表时间:
2012-12
期刊:
Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference
影响因子:
--
通讯作者:
Satoshi Ikehata;K. Aizawa
Satoshi Ikehata;K. Aizawa
中科院分区:
其他
文献类型:
--
作者:
Satoshi Ikehata;K. Aizawa

文献摘要

相似文献

本文提出了一个实用的深度图细化系统设计的高度损坏的多个深度图。我们定义了一个像素级的深度值的置信度度量,并应用三步深度图细化方案(即基于置信度的深度图融合,置信度加权束优化和基于超像素的平面传播),以最大限度地提高深度图的整体可靠性。我们的实验结果表明,我们的细化算法可以显着改善以前的方法获得的高度损坏的深度图。
This paper present a practical depth-map refinement system designed for highly corrupted multiple depth maps. We define a pixel-wise confidence measurement of depth value and apply the three-steps depth-map refinement scheme (i.e.confidence-based depth-map fusion, confidence-weighted bundle optimization and super-pixel-based planar propagation) to maximize the whole reliability of depth maps. Our experimental result shows that our refinement algorithm can dramatically improve highly corrupted depth maps acquired by previous approaches.