Korea Advanced Institute of Science and Technology, Daejeon.
IEEE Trans Pattern Anal Mach Intell. 2014 Feb;36(2):209-21. doi: 10.1109/TPAMI.2013.45.
We propose a physically-based approach to separate reflection using multiple polarized images with a background scene captured behind glass. The input consists of three polarized images, each captured from the same view point but with a different polarizer angle separated by 45 degrees. The output is the high-quality separation of the reflection and background layers from each of the input images. A main technical challenge for this problem is that the mixing coefficient for the reflection and background layers depends on the angle of incidence and the orientation of the plane of incidence, which are spatially varying over the pixels of an image. Exploiting physical properties of polarization for a double-surfaced glass medium, we propose a multiscale scheme which automatically finds the optimal separation of the reflection and background layers. Through experiments, we demonstrate that our approach can generate superior results to those of previous methods.
我们提出了一种基于物理的方法，通过拍摄玻璃后面背景场景的三张不同偏光角度相差 45 度的偏光图像来分离反射。输入图像由三张来自同一视角的偏光图像组成，输出图像是从每张输入图像中分离出高质量的反射层和背景层。对于这个问题，主要的技术挑战是反射层和背景层的混合系数取决于入射角和入射平面的方向，这些参数在图像的像素上是空间变化的。利用双面玻璃介质的偏振物理特性，我们提出了一种多尺度方案，可以自动找到反射层和背景层的最佳分离。通过实验，我们证明了我们的方法可以产生优于以前方法的结果。
