Enabling Artistic Control Over Pattern Density and Stroke Strength
Journal
IEEE TRANSACTIONS ON MULTIMEDIA
Journal Volume
23
Pages
2273
Date Issued
2021
Author(s)
Abstract
Despite the remarkable results and numerous advancements in neural style transfer, achieving artistic control is still a challenging feat, primarily since existing methodologies treat the style representation as a black-box model. This oversight significantly limits the range of possible artistic manipulations. In this paper, we propose a method to enable artistic control on any correlation-based style transfer models along with guiding intuitions. Our focus is on controlling two perceptual factors: Pattern Density and Stroke Strength. To achieve this, we introduce the centered Gram style representation and manipulate it with our variance-aware adaptive weighting and correlation-based selective masking. Through several experiments and comparisons with the state-of-the-art, we show that we can achieve artistic control with competitive stylization quality. Additionally, since our method involves manipulating style representation, it can easily be adapted to popular style transfer models. We analyze different style representation properties to propose rules that govern the style transfer process, which is critical towards achieving artistic control over pattern density and stroke strength.
Subjects
Correlation; Feature extraction; Image resolution; Adaptation models; Network architecture; Integrated circuits; Image color analysis; Style transfer control; style representation
SDGs
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Type
journal article