How to Train Neural Networks for Flare Removal
How to Train Neural Networks for Flare Removal
复制标题
DOI：
10.1109/iccv48922.2021.00224
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Yichen Wu;Qiurui He;Tianfan Xue;Rahul Garg;Jiawen Chen;A. Veeraraghavan;J. Barron
中科院分区：
文献类型：
--
作者：
Yichen Wu;Qiurui He;Tianfan Xue;Rahul Garg;Jiawen Chen;A. Veeraraghavan;J. Barron
当相机指向强光源时，所产生的照片可能包含透镜光斑伪影。耀斑出现在各种各样的模式（晕，条纹，颜色出血，阴霾等）。并且这种外观上的多样性使得耀斑去除具有挑战性。现有的解析解对伪影的几何形状或亮度做了很强的假设，因此只能在一小部分耀斑上工作得很好。机器学习技术在去除其他类型的伪影（如反射）方面取得了成功，但由于缺乏训练数据，尚未广泛应用于耀斑去除。为了解决这个问题，我们明确地模拟耀斑的光学原因，无论是经验或使用波动光学，并产生半合成对耀斑损坏和干净的图像。这使我们能够训练神经网络，以消除透镜耀斑的第一次。实验表明，我们的数据合成方法对于准确去除眩光至关重要，并且使用我们的技术训练的模型可以很好地推广到不同场景，照明条件和相机的真实的透镜眩光。
When a camera is pointed at a strong light source, the resulting photograph may contain lens flare artifacts. Flares appear in a wide variety of patterns (halos, streaks, color bleeding, haze, etc.) and this diversity in appearance makes flare removal challenging. Existing analytical solutions make strong assumptions about the artifact’s geometry or brightness, and therefore only work well on a small subset of flares. Machine learning techniques have shown success in removing other types of artifacts, like reflections, but have not been widely applied to flare removal due to the lack of training data. To solve this problem, we explicitly model the optical causes of flare either empirically or using wave optics, and generate semi-synthetic pairs of flare-corrupted and clean images. This enables us to train neural networks to remove lens flare for the first time. Experiments show our data synthesis approach is critical for accurate flare removal, and that models trained with our technique generalize well to real lens flares across different scenes, lighting conditions, and cameras.