Dual Pipeline Style Transfer with Input Distribution Differentiation
This addresses texture artifacts in style transfer for image processing applications, representing an incremental improvement.
The paper tackles the problem of texture artifacts in style transfer by showing that input distribution differentiation, not smooth inputs, is key to suppressing textures. They propose an input distribution differentiation training strategy that achieves complete texture elimination in color transfer tasks.
The color and texture dual pipeline architecture (CTDP) suppresses texture representation and artifacts through masked total variation loss (Mtv), and further experiments have shown that smooth input can almost completely eliminate texture representation. We have demonstrated through experiments that smooth input is not the key reason for removing texture representations, but rather the distribution differentiation of the training dataset. Based on this, we propose an input distribution differentiation training strategy (IDD), which forces the generation of textures to be completely dependent on the noise distribution, while the smooth distribution will not produce textures at all. Overall, our proposed distribution differentiation training strategy allows for two pre-defined input distributions to be responsible for two generation tasks, with noise distribution responsible for texture generation and smooth distribution responsible for color smooth transfer. Finally, we choose a smooth distribution as the input for the forward inference stage to completely eliminate texture representations and artifacts in color transfer tasks.