论文标题
在野外完全排列的偏振反射去除
Polarized Reflection Removal with Perfect Alignment in the Wild
论文作者
论文摘要
我们提出了一种新的配方，可以从野外偏振图像中取消反射。我们首先确定现有反射删除数据集的不一致问题，在这些问题中，由于玻璃折射，收集的无反射图像与输入混合图像并未完全对齐。然后，我们构建了一个具有100多种玻璃的新数据集，其中获得的传输图像与输入混合图像完美对齐。其次，利用反射和偏光光之间的特殊关系，我们提出了一个具有两阶段架构的偏振反射拆卸模型。此外，我们设计了一种新颖的知觉NCC损失，可以改善反射去除和一般图像分解任务的性能。我们进行了广泛的实验，结果表明，我们的模型优于删除反射的最先进方法。
We present a novel formulation to removing reflection from polarized images in the wild. We first identify the misalignment issues of existing reflection removal datasets where the collected reflection-free images are not perfectly aligned with input mixed images due to glass refraction. Then we build a new dataset with more than 100 types of glass in which obtained transmission images are perfectly aligned with input mixed images. Second, capitalizing on the special relationship between reflection and polarized light, we propose a polarized reflection removal model with a two-stage architecture. In addition, we design a novel perceptual NCC loss that can improve the performance of reflection removal and general image decomposition tasks. We conduct extensive experiments, and results suggest that our model outperforms state-of-the-art methods on reflection removal.
