Depth-aware Neural Style Transfer using Instance Normalization

TL;DR

This paper introduces a depth-aware neural style transfer method that integrates depth preservation into the stylization process, resulting in more structurally consistent and aesthetically pleasing stylized images.

Contribution

It proposes a novel neural style transfer approach that incorporates depth information via an additional loss function, improving depth and structure preservation in stylized images.

Findings

Effective depth and structure retention demonstrated

Comparable or superior style capture and aesthetic quality

Validated through three evaluation processes

Abstract

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.