Photorealistic Style Transfer via Wavelet Transforms

TL;DR

This paper introduces WCT$^2$, a wavelet-based neural network method that achieves photorealistic style transfer efficiently at high resolution, preserving image structure and enabling stable video stylization.

Contribution

The paper presents a novel wavelet transform-based correction to style transfer networks, enabling high-resolution, photorealistic stylization with real-time performance and stability in video.

Findings

Stylizes 1024x1024 images in 4.7 seconds.

Produces photorealistic results without post-processing.

Supports stable video stylization.

Abstract

Recent style transfer models have provided promising artistic results. However, given a photograph as a reference style, existing methods are limited by spatial distortions or unrealistic artifacts, which should not happen in real photographs. We introduce a theoretically sound correction to the network architecture that remarkably enhances photorealism and faithfully transfers the style. The key ingredient of our method is wavelet transforms that naturally fits in deep networks. We propose a wavelet corrected transfer based on whitening and coloring transforms (WCT$^2$) that allows features to preserve their structural information and statistical properties of VGG feature space during stylization. This is the first and the only end-to-end model that can stylize a $1024\times1024$ resolution image in 4.7 seconds, giving a pleasing and photorealistic quality without any post-processing. Last but not least, our model provides a stable video stylization without temporal constraints. Our code, generated images, and pre-trained models are all available at https://github.com/ClovaAI/WCT2.