Interactive Multi-level Stroke Control for Neural Style Transfer

TL;DR

StyleTune is a mobile app that offers interactive multi-level control over neural style transfer, allowing users to adjust style elements like stroke size, orientation, and texture with high fidelity and resolution.

Contribution

We introduce a novel stroke-adaptive style transfer network and a network-agnostic stroke orientation adjustment method for enhanced user control in neural style transfer.

Findings

Supports stroke size and orientation adjustments

Enables high-resolution outputs over 20 Megapixels

Provides more creative control than existing apps

Abstract

We present StyleTune, a mobile app for interactive multi-level control of neural style transfers that facilitates creative adjustments of style elements and enables high output fidelity. In contrast to current mobile neural style transfer apps, StyleTune supports users to adjust both the size and orientation of style elements, such as brushstrokes and texture patches, on a global as well as local level. To this end, we propose a novel stroke-adaptive feed-forward style transfer network, that enables control over stroke size and intensity and allows a larger range of edits than current approaches. For additional level-of-control, we propose a network agnostic method for stroke-orientation adjustment by utilizing the rotation-variance of CNNs. To achieve high output fidelity, we further add a patch-based style transfer method that enables users to obtain output resolutions of more than 20 Megapixel. Our approach empowers users to create many novel results that are not possible with current mobile neural style transfer apps.