Deriving intrinsic images from image sequences
Deriving intrinsic images from image sequences
复制标题
DOI：
10.1109/iccv.2001.937606
复制
发表时间：
2001-07
期刊：
影响因子：
--
通讯作者：
Yair Weiss
中科院分区：
文献类型：
--
作者：
Yair Weiss
内在图像是 H.G. Barrow 和 J.M. Tenenbaum (1978) 提出的一种有用的场景中级描述。图像被分解为两个图像：反射图像和照明图像。找到这样的分解仍然是计算机视觉中的一个难题。我们关注一个稍微简单一点的问题：给定一系列反射率恒定且光照变化的 T 图像，我们可以恢复 T 光照图像和单个反射率图像吗？我们表明这个问题仍然存在，并建议将其视为最大似然估计问题。在最近关于自然图像统计的工作之后，我们使用先验假设照明图像将产生稀疏滤波器输出。我们证明这导致了一种简单、新颖的算法来恢复反射图像。我们说明了该算法在真实和合成图像序列上的性能。
Intrinsic images are a useful midlevel description of scenes proposed by H.G. Barrow and J.M. Tenenbaum (1978). An image is de-composed into two images: a reflectance image and an illumination image. Finding such a decomposition remains a difficult problem in computer vision. We focus on a slightly, easier problem: given a sequence of T images where the reflectance is constant and the illumination changes, can we recover T illumination images and a single reflectance image? We show that this problem is still imposed and suggest approaching it as a maximum-likelihood estimation problem. Following recent work on the statistics of natural images, we use a prior that assumes that illumination images will give rise to sparse filter outputs. We show that this leads to a simple, novel algorithm for recovering reflectance images. We illustrate the algorithm's performance on real and synthetic image sequences.