TY  - JOUR
A1  - Reimann, Max
A1  - Buchheim, Benito
A1  - Semmo, Amir
A1  - Döllner, Jürgen
A1  - Trapp, Matthias
T1  - Controlling strokes in fast neural style transfer using content transforms
JF  - The Visual Computer
N2  - Fast style transfer methods have recently gained popularity in art-related applications as they make a generalized real-time stylization of images practicable. However, they are mostly limited to one-shot stylizations concerning the interactive adjustment of style elements. In particular, the expressive control over stroke sizes or stroke orientations remains an open challenge. To this end, we propose a novel stroke-adjustable fast style transfer network that enables simultaneous control over the stroke size and intensity, and allows a wider range of expressive editing than current approaches by utilizing the scale-variance of convolutional neural networks. Furthermore, we introduce a network-agnostic approach for style-element editing by applying reversible input transformations that can adjust strokes in the stylized output. At this, stroke orientations can be adjusted, and warping-based effects can be applied to stylistic elements, such as swirls or waves. To demonstrate the real-world applicability of our approach, we present StyleTune, a mobile app for interactive editing of neural style transfers at multiple levels of control. Our app allows stroke adjustments on a global and local level. It furthermore implements an on-device patch-based upsampling step that enables users to achieve results with high output fidelity and resolutions of more than 20 megapixels. Our approach allows users to art-direct their creations and achieve results that are not possible with current style transfer applications.
Y1  - 2022
U6  - https://doi.org/10.1007/s00371-022-02518-x
SN  - 0178-2789
SN  - 1432-2315
VL  - 38
IS  - 12
SP  - 4019
EP  - 4033
PB  - Springer
CY  - New York
ER  -