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.

Population Genomics of Cotton

“…The paper [3] provides an overview of various methods for neural style transfer in computer graphics and computer vision. The review covers different approaches, including those based on convolutional neural networks (CNNs), generative adversarial networks (GANs), and patch-based methods.…”

Neural Style Transfer: A Critical Review

“…The depth map of the content image cannot be replicated. [22] proposed an extension to the AdaIn method to preserve the depth map by applying variable stylization strength. The comparison showed in the image Fig.…”