MSCE: An edge preserving robust loss function for improving super-resolution algorithms.
arXiv: Computer Vision and Pattern Recognition(2018)
摘要
With the recent advancement in the deep learning technologies such as CNNs and GANs, there is significant improvement in the quality of the images reconstructed by deep learning based super-resolution (SR) techniques. In this work, we propose a robust loss function based on the preservation of edges obtained by the Canny operator. This loss function, when combined with the existing loss function such as mean square error (MSE), gives better SR reconstruction measured in terms of PSNR and SSIM. Our proposed loss function guarantees improved performance on any existing algorithm using MSE loss function, without any increase in the computational complexity during testing.
更多查看译文
关键词
Loss function, CNN, GAN, Super-resolution, Mean square error, Mean square Canny error, Edge preservation, PSNR, SSIM
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要