Enabling Artistic Control over Pattern Density and Stroke Strength

John Jethro Virtusio, Daniel Stanley Tan, Wen-Huang Cheng, M. Tanveer, Kai Lung Hua*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

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.

Original languageEnglish
Article number9143296
Pages (from-to)2273-2285
Number of pages13
JournalIEEE Transactions on Multimedia
Volume23
DOIs
StatePublished - 17 Jul 2021

Keywords

  • style representation
  • Style transfer control

Fingerprint

Dive into the research topics of 'Enabling Artistic Control over Pattern Density and Stroke Strength'. Together they form a unique fingerprint.

Cite this