Regional Style and Color Transfer

TL;DR

This paper introduces a regional style transfer method that uses segmentation to isolate foreground objects, applies style transfer to backgrounds only, and then reintegrates the foreground with color adjustments for more natural results.

Contribution

A novel approach that combines segmentation, selective style transfer, and color adjustment to improve regional style transfer quality.

Findings

More natural stylistic transformations achieved

Enhanced visual coherence between foreground and background

Superior to conventional style transfer methods

Abstract

This paper presents a novel contribution to the field of regional style transfer. Existing methods often suffer from the drawback of applying style homogeneously across the entire image, leading to stylistic inconsistencies or foreground object twisted when applied to image with foreground elements such as person figures. To address this limitation, we propose a new approach that leverages a segmentation network to precisely isolate foreground objects within the input image. Subsequently, style transfer is applied exclusively to the background region. The isolated foreground objects are then carefully reintegrated into the style-transferred background. To enhance the visual coherence between foreground and background, a color transfer step is employed on the foreground elements prior to their rein-corporation. Finally, we utilize feathering techniques to achieve a seamless amalgamation of foreground and background, resulting in a visually unified and aesthetically pleasing final composition. Extensive evaluations demonstrate that our proposed approach yields significantly more natural stylistic transformations compared to conventional methods.