Image Style Transfer Method Based on Improved Style Loss Function
Hanmin Ye, Wenjie Liu, Yingzhi Liu · 2020
In order to improve the quality of composite image in the process of image style transfer. This paper proposes an image style transfer method based on an improved style loss function: the improved Gram matrix calculates the inner product of the feature map and the spatial transformation map, and then calculates the new style loss function. At the same time, combined with the content loss function, the weighted algebraic sum of the two loss functions is used as the total loss function of the neural network. The gradient descent algorithm is used to iteratively optimize to generate the style-transferred image. Experimental results show that the Peak Signal to Noise Ratio and Structural Similarity values of this method are better than other style transfer algorithms, and the image texture details and spatial arrangement are more complete.