Article: Pseudo-coordinates graph convolutional generative adversarial network for art style transfer Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.6 pp.45 - 61 Abstract: The goal of style transfer is to apply the artistic features of a style image to a content image while maintaining the content image's structure. Traditional methods often use CNNs and residual blocks, but their limited receptive field struggles to capture long-range feature dependencies, leading to repetitive local patterns. Residual blocks can also cause interference between style and content representations. To address these issues, we introduce a pseudo-coordinates graph convolutional generative adversarial network (PGC-GAN), which consists of two branches: one for extracting style and another for style transfer. The style extraction branch represents style features as a graph and uses graph pooling to remove redundant information. The style transfer branch encodes these features into pseudo-coordinates, enabling flexible relationships between pixel nodes and long-range feature aggregation without disrupting the content image's structure. Experimental results demonstrate that PGC-GAN significantly improves artistic style transfer compared to existing methods. Inderscience Publishers - linking academia, business and industry through research

Title: Pseudo-coordinates graph convolutional generative adversarial network for art style transfer

Authors: Feng Wang; Zihan Zhang

Addresses: Office of Academic Affairs, Jiangsu Vocational Institute of Architectural Technology, Xuzhou, Jiangsu, 221116, China ' Office of Academic Affairs, Jiangsu Vocational Institute of Architectural Technology, Xuzhou, Jiangsu, 221116, China

Abstract: The goal of style transfer is to apply the artistic features of a style image to a content image while maintaining the content image's structure. Traditional methods often use CNNs and residual blocks, but their limited receptive field struggles to capture long-range feature dependencies, leading to repetitive local patterns. Residual blocks can also cause interference between style and content representations. To address these issues, we introduce a pseudo-coordinates graph convolutional generative adversarial network (PGC-GAN), which consists of two branches: one for extracting style and another for style transfer. The style extraction branch represents style features as a graph and uses graph pooling to remove redundant information. The style transfer branch encodes these features into pseudo-coordinates, enabling flexible relationships between pixel nodes and long-range feature aggregation without disrupting the content image's structure. Experimental results demonstrate that PGC-GAN significantly improves artistic style transfer compared to existing methods.

Keywords: art style transfer; graph convolution; pseudo-coordinates; GAN.

DOI: 10.1504/IJICT.2025.145402

International Journal of Information and Communication Technology, 2025 Vol.26 No.6, pp.45 - 61

Received: 28 Nov 2024
Accepted: 20 Jan 2025
Published online: 31 Mar 2025 *

Title: Pseudo-coordinates graph convolutional generative adversarial network for art style transfer

Keep up-to-date