GAN-based image deblurring using DCT loss with customized datasets
GAN-based image deblurring using DCT loss with customized datasets
复制标题
DOI：
10.1109/access.2021.3116194
复制
发表时间：
2021
期刊：
影响因子：
3.9
通讯作者：
Hiroki Tomosada;Takahiro Kudo;Takanori Fujisawa;M. Ikehara
中科院分区：
文献类型：
--
作者：
Hiroki Tomosada;Takahiro Kudo;Takanori Fujisawa;M. Ikehara
在本文中，我们提出了一个高品质的图像去模糊方法，使用离散余弦变换（DCT），需要较少的计算复杂度。我们在一个新的数据集上训练我们的模型，该数据集被定制为包括具有大运动模糊的图像。最近，卷积神经网络（CNN）和生成对抗网络（GAN）为基础的算法已经提出了图像去模糊。此外，CNN的多尺度和多补丁架构可以清晰地恢复模糊图像，并抑制更多的振铃或块效应，但它们需要更长的时间来处理。为了提高去模糊图像的质量和减少计算时间，我们提出了一种称为“DeflurDCTGAN”的方法，该方法使用基于DCT的损失在频域中比较恢复图像和地面真实图像，在不使用多尺度或多块结构的情况下保留恢复图像中的纹理并抑制振铃伪影。利用这种损失，DeflurDCTGAN可以减少块噪声和振铃伪影，同时保持去模糊性能。我们的实验结果表明，去模糊DCTGAN得到最高的性能在PSNR，SSIM，和运行时间相比，传统的方法。在真实的图像数据集方面，通过使用由GoPro，DVD，NFS和HIDE训练数据集制成的自定义训练数据集，DeflurDCTGAN显示出更好的性能。具有预训练权重、数据集和结果的实验代码可在https://github.com/Hiroki-Tomosada/DCTGAN-master上获得。
In this paper, we propose a high quality image deblurring method that uses discrete cosine transform (DCT) and requires less computational complexity. We train our model on a new dataset which is customized to include images with large motion blurs. Recently, Convolutional Neural Network (CNN) and Generative Adversarial Network (GAN) based algorithms have been proposed for image deblurring. Moreover, multi-scale and multi-patch architectures of CNN restore blurred images clearly and suppress more ringing or blocking artifacts, but they take a longer time to process. To improve the quality of deblured images and reduce the computational time, we propose a method called "DeblurDCTGAN" that preserves texture and suppresses ringing artifacts in the restored image without multi-scale or multi-patch architecture using DCT based loss.This loss compares the restored image and the ground truth image in the frequency domain. With this loss, DeblurDCTGAN can reduce block noise and ringing artifacts while maintaining deblurring performance. Our experimental results show that DeblurDCTGAN gets the highest performances in terms of PSNR, SSIM, and running time compared with conventional methods. In terms of real image datasets, DeblurDCTGAN shows a better performance by using a customized training dataset made from GoPro, DVD, NFS and HIDE training datasets. Experimented code with pre-trained weights, datasets and results are available at https://github.com/Hiroki-Tomosada/DCTGAN-master.