论文标题
逼真的模糊
Deblurring by Realistic Blurring
论文作者
论文摘要
现有的图像脱毛的深度学习方法通常使用成对的锋利图像及其模糊的对应物训练模型。但是，合成模糊的图像并不一定会以足够的精度对真实情况进行真实的模糊过程进行建模。为了解决这个问题，我们提出了一种新方法，该方法结合了两个GAN模型，即学习到Blur gan（bgan）和学习到deblur gan（dbgan），以通过主要学习如何模糊图像来学习一个更好的图像debluring模型。第一个模型BGAN学会了如何使用未配对的锋利和模糊图像集模糊锋利的图像，然后引导第二个模型DBGAN学习如何正确删除此类图像。为了减少实际模糊和合成模糊之间的差异，利用相对论的模糊损失。作为另一个贡献，本文还引入了现实世界模糊的图像（RWBI）数据集，包括不同的模糊图像。我们的实验表明，所提出的方法在新提出的数据集和公共GOPRO数据集上始终达到卓越的定量性能以及更高的感知质量。
Existing deep learning methods for image deblurring typically train models using pairs of sharp images and their blurred counterparts. However, synthetically blurring images do not necessarily model the genuine blurring process in real-world scenarios with sufficient accuracy. To address this problem, we propose a new method which combines two GAN models, i.e., a learning-to-Blur GAN (BGAN) and learning-to-DeBlur GAN (DBGAN), in order to learn a better model for image deblurring by primarily learning how to blur images. The first model, BGAN, learns how to blur sharp images with unpaired sharp and blurry image sets, and then guides the second model, DBGAN, to learn how to correctly deblur such images. In order to reduce the discrepancy between real blur and synthesized blur, a relativistic blur loss is leveraged. As an additional contribution, this paper also introduces a Real-World Blurred Image (RWBI) dataset including diverse blurry images. Our experiments show that the proposed method achieves consistently superior quantitative performance as well as higher perceptual quality on both the newly proposed dataset and the public GOPRO dataset.
