machine-learning - How to remove deconvolution noise in style-transfer neural network

Question

Im studying style-transfer networks and right now working with this work and here is network description. The problem that even with adding TV loss there is still visible noise which is breaking quality of result. Can someone recommend some articles of ways of removing such noise during network training?

Thanks

Answer 1

噪声是由于输入和内核之间的deconvolution不均匀重叠造成的，这会产生不同幅度的棋盘状模式。一种解决方法是使用本文resize-conv中提到的方法。

Resize-conv替换transpose convolution为image scaling 后跟一个2D convolution. 在张量流中，两个步骤是：tf.image.resize_images(...)和tf.nn.conv2d(...)。作者的另一个提示是tf.pad(...)在卷积方法之前调用并且只使用Nearest Neighbourresize 方法。