论文标题
不仅是条纹：迈向地面真理，以使单图像降低
Not Just Streaks: Towards Ground Truth for Single Image Deraining
论文作者
论文摘要
我们提出了一个大规模的雨天和干净的图像对数据集，以及一种从图像中消除降雨和雨水积累引起的降解的方法。由于没有现实世界中的数据集，因此当前的最新方法依赖于合成数据，因此受SIM2REAL域间隙的限制。此外，由于没有真实的配对数据集，严格的评估仍然是一个挑战。我们通过细致地控制非洪水变化来收集真实的配对数据集来填补这一空白。我们的数据集可实现对不同现实世界现象的配对训练和定量评估（例如，雨条和雨水积累）。为了学习强大的雨水现象，我们提出了一个深层的神经网络，该网络通过最大程度地减少雨水和干净图像之间的雨水损失来重建基础场景。广泛的实验表明，在各种条件下，我们的模型在真实雨水图像上的最先进方法优于最先进的方法。项目网站：https：//visual.ee.ucla.edu/gt_rain.htm/。
We propose a large-scale dataset of real-world rainy and clean image pairs and a method to remove degradations, induced by rain streaks and rain accumulation, from the image. As there exists no real-world dataset for deraining, current state-of-the-art methods rely on synthetic data and thus are limited by the sim2real domain gap; moreover, rigorous evaluation remains a challenge due to the absence of a real paired dataset. We fill this gap by collecting a real paired deraining dataset through meticulous control of non-rain variations. Our dataset enables paired training and quantitative evaluation for diverse real-world rain phenomena (e.g. rain streaks and rain accumulation). To learn a representation robust to rain phenomena, we propose a deep neural network that reconstructs the underlying scene by minimizing a rain-robust loss between rainy and clean images. Extensive experiments demonstrate that our model outperforms the state-of-the-art deraining methods on real rainy images under various conditions. Project website: https://visual.ee.ucla.edu/gt_rain.htm/.
