Depth-aware Neural Style Transfer using Instance Normalization
This addresses depth distortion issues in artistic stylization for users of neural style transfer, but it is incremental as it builds on existing methods with an added depth component.
The paper tackles the problem of preserving depth in neural style transfer when content images have multiple objects at varying depths, by integrating depth prediction into the loss function, resulting in effective depth retention and structure preservation with style-capture comparable or superior to state-of-the-art methods.
Neural Style Transfer (NST) is concerned with the artistic stylization of visual media. It can be described as the process of transferring the style of an artistic image onto an ordinary photograph. Recently, a number of studies have considered the enhancement of the depth-preserving capabilities of the NST algorithms to address the undesired effects that occur when the input content images include numerous objects at various depths. Our approach uses a deep residual convolutional network with instance normalization layers that utilizes an advanced depth prediction network to integrate depth preservation as an additional loss function to content and style. We demonstrate results that are effective in retaining the depth and global structure of content images. Three different evaluation processes show that our system is capable of preserving the structure of the stylized results while exhibiting style-capture capabilities and aesthetic qualities comparable or superior to state-of-the-art methods. Project page: https://ioannoue.github.io/depth-aware-nst-using-in.html.