Combining Bottom-Up and Top-Down Visual Mechanisms for Color Constancy Under Varying Illumination
Combining Bottom-Up and Top-Down Visual Mechanisms for Color Constancy Under Varying Illumination
复制标题
结合自下而上和自上而下的视觉机制，以确保不同照明下的颜色恒定性
DOI：
10.1109/tip.2019.2908783
复制
发表时间：
2019-09-01
影响因子：
10.6
通讯作者：
Li, Yong-Jie
中科院分区：
文献类型：
--
作者：
Gao, Shao-Bing;Ren, Yan-Ze;Li, Yong-Jie
基于多光源的颜色恒定(MCC)是一项颇具挑战性的任务。本文根据人类视觉系统的自下而上和自上而下机制，提出了一种新的模型来估计场景中光照的空间变化。基于自下而上的估计的动机来自我们的发现，场景中的亮部分和暗部分在编码光源方面扮演着不同的角色。然而，使用纯自下而上处理很难处理大型彩色对象的色移。因此，我们进一步引入了受视觉心理物理学发现启发的自上而下的约束，其中高层信息(例如，光源颜色的先验信息)在视觉颜色恒定中起着关键作用。为了实现自上而下的假设，我们只需学习通过自下而上处理估计的光源分布与数据集提供的地面真实地图之间的颜色映射。我们在四个数据集上对我们的模型进行了评估，结果表明，我们的方法与最先进的MCC算法相比获得了非常好的性能。此外，考虑到我们的结果是使用所有数据集的相同参数获得的，或者我们模型的参数是从输入中学习的，即模仿人类视觉系统的运行方式，因此我们模型的稳健性更明显。我们还给出了一些来自网络的真实图像的颜色校正结果。
Multi-illuminant-based color constancy (MCC) is quite a challenging task. In this paper, we proposed a novel model motivated by the bottom-up and top-down mechanisms of human visual system (HVS) to estimate the spatially varying illumination in a scene. The motivation for bottom-up based estimation is from our finding that the bright and dark parts in a scene play different roles in encoding illuminants. However, handling the color shift of large colorful objects is difficult using pure bottom-up processing. Thus, we further introduce a top-down constraint inspired by the findings in visual psychophysics, in which high-level information (e.g., the prior of light source colors) plays a key role in visual color constancy. In order to implement the top-down hypothesis, we simply learn a color mapping between the illuminant distribution estimated by bottom-up processing and the ground truth maps provided by the dataset. We evaluated our model on four datasets and the results show that our method obtains very competitive performance compared with the state-of-the-art MCC algorithms. Moreover, the robustness of our model is more tangible considering that our results were obtained using the same parameters for all the datasets or the parameters of our model were learned from the inputs, that is, mimicking how HVS operates. We also show the color correction results on some real-world images taken from the web.