A Method for Arbitrary Instance Style Transfer

TL;DR

This paper introduces Forward Stretching, a topologically inspired algorithm that enables style transfer to arbitrary-shaped instances by transforming them into tensor representations, expanding style transfer capabilities beyond whole images.

Contribution

The paper presents a novel tensor-based method for transferring style to arbitrary-shaped instances, addressing limitations of previous whole-image style transfer techniques.

Findings

Successfully transfers style to arbitrary-shaped instances

Enables style transfer in complex and irregular shapes

Demonstrates effectiveness through experimental results

Abstract

The ability to synthesize style and content of different images to form a visually coherent image holds great promise in various applications such as stylistic painting, design prototyping, image editing, and augmented reality. However, the majority of works in image style transfer have focused on transferring the style of an image to the entirety of another image, and only a very small number of works have experimented on methods to transfer style to an instance of another image. Researchers have proposed methods to circumvent the difficulty of transferring style to an instance in an arbitrary shape. In this paper, we propose a topologically inspired algorithm called Forward Stretching to tackle this problem by transforming an instance into a tensor representation, which allows us to transfer style to this instance itself directly. Forward Stretching maps pixels to specific positions and interpolate values between pixels to transform an instance to a tensor. This algorithm allows us to introduce a method to transfer arbitrary style to an instance in an arbitrary shape. We showcase the results of our method in this paper.