1. AI-Enhanced Digital Creativity Design: Content-Style Alignment for Image Stylization
- Author
-
Lanting Yu and Qiang Zheng
- Subjects
Deep learning ,stylization ,encoder-decoder structure ,VGG ,Electrical engineering. Electronics. Nuclear engineering ,TK1-9971 - Abstract
This paper presents an AI(Artificial Intelligence)-powered method for enhancing digital creative design through image stylization. To achieve this, we introduce the Content-Style Alignment Module (CSAM), which includes the Dual-Stream Content-Style Processing Block (DS-CSPB), Content-Style Matching Attention Block (CS-MAB), and Content-Style Space-Aware Interpolation Block (CS-SAIB). DS-CSPB removes style information from content descriptors using whitening transformation while preserving semantic structures. CS-MAB reorganizes each content descriptor with its most relevant style descriptor, ensuring optimal style adaptation for content semantics. CS-SAIB aligns content and style descriptors in the same space, enabling diverse semantic distributions in content images to match various style patterns. Moreover, we introduce the Multifaceted Optimization Loss (MOL). This loss comprises multiple components: The relaxed Earth Mover Distance (rEMD) loss enhances color and texture distributions on content images. The Moment Matching (MM) loss reduces visual artifacts caused by cosine distance. The differentiable Color Histogram (CH) loss efficiently addresses color blending issues, preserving image naturalness. The content loss ensures no significant deformation or distortion during stylization. The reconstruction loss constrains all encoder-decoder features to the VGG feature space, maintaining shared spaces between content and style descriptors. We conducted extensive comparative and ablation experiments, which demonstrated superior performance in image stylization, resulting in high-quality stylized images. Additionally, we provide a comprehensive review of current research in image stylization, effectively bridging the gap in this area.
- Published
- 2023
- Full Text
- View/download PDF