Depth-Aware Arbitrary Style Transfer Using Instance Normalization
Abstract
Style transfer is the process of rendering one image with some content in the style of another image, representing the style. Recent studies of Liu et al. (2017) show that traditional style transfer methods of Gatys et al. (2016) and Johnson et al. (2016) fail to reproduce the depth of the content image, which is critical for human perception. They suggest to preserve the depth map by additional regularizer in the optimized loss function, forcing preservation of the depth map. However these traditional methods are either computationally inefficient or require training a separate neural network for each style. AdaIN method of Huang et al. (2017) allows efficient transferring of arbitrary style without training a separate model but is not able to reproduce the depth map of the content image. We propose an extension to this method, allowing depth map preservation by applying variable stylization strength. Qualitative analysis and results of user evaluation study indicate that the proposed method provides better stylizations, compared to the original AdaIN style transfer method.
Cite
@article{arxiv.1906.01123,
title = {Depth-Aware Arbitrary Style Transfer Using Instance Normalization},
author = {Victor Kitov and Konstantin Kozlovtsev and Margarita Mishustina},
journal= {arXiv preprint arXiv:1906.01123},
year = {2020}
}
Comments
Replacement of the previous version due to the following improvements: depth estimation methods comparison added, better depth estimation network used, transformation to proximity map added with offset and contrast parameters. Dependency on these parameters shown, comparison of AdaIN and proposed method added, user evaluation study completely remade for improved version of the proposed method