Refractive height fields from single and multiple images

Refractive height fields from single and multiple images
复制标题

DOI:
10.1109/cvpr.2012.6247687
复制
发表时间:
2012-06
期刊:
2012 IEEE Conference on Computer Vision and Pattern Recognition
影响因子:
--
通讯作者:
Qi Shan;Sameer Agarwal;B. Curless
Qi Shan;Sameer Agarwal;B. Curless
中科院分区:
其他
文献类型:
--
作者:
Qi Shan;Sameer Agarwal;B. Curless

文献摘要

被引文献

相似文献

我们提出了一个新的框架,从一个单一的观点重建均匀,透明,折射高度场。高度场相对于已知的平面背景或背景序列成像。与现有的逐点重建方法不同(已知其具有难以处理的模糊性),我们的方法同时对整个高度场进行估计和优化。该配方支持从测量的失真(偏转)或直接从图像本身,包括从一个单一的图像的形状恢复。我们报告了各种折射高度场的结果,显示出比现有技术的显着改善。
We propose a novel framework for reconstructing homogenous, transparent, refractive height-fields from a single viewpoint. The height-field is imaged against a known planar background, or sequence of backgrounds. Unlike existing approaches that do a point-by-point reconstruction - which is known to have intractable ambiguities - our method estimates and optimizes for the entire height-field at the same time. The formulation supports shape recovery from measured distortions (deflections) or directly from the images themselves, including from a single image. We report results for a variety of refractive height-fields showing significant improvement over prior art.