Meta Network for Flow-Based Image Style Transfer

doi:10.3390/electronics14102035

機構典藏 > College of Engineering > Graduate Institute & Department of Computer Science and Information Engineering > Journal Article > Item 987654321/127370

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/127370

Title:	Meta Network for Flow-Based Image Style Transfer
Authors:	Yu, Yihjia Tsai；Hsiau-Wen Lin；Hwei Jen Lin；Chii-Jen Chen；Chen-Hsiang
Keywords:	meta learning;image style transfer;convolutional neural network;instance normalization;adversarial learning;flow-based model
Date:	2025-05-16
Issue Date:	2025-05-23 12:05:13 (UTC+8)
Publisher:	Multidisciplinary Digital Publishing Institute
Abstract:	A style transfer aims to produce synthesized images that retain the content of one image while adopting the artistic style of another. Traditional style transfer methods often require training separate transformation networks for each new style, limiting their adaptability and scalability. To address this challenge, we propose a flow-based image style transfer framework that integrates Randomized Hierarchy Flow (RH Flow) and a meta network for adaptive parameter generation. The meta network dynamically produces the RH Flow parameters conditioned on the style image, enabling efficient and flexible style adaptation without retraining for new styles. RH Flow enhances feature interaction by introducing a random permutation of the feature sub-blocks before hierarchical coupling, promoting diverse and expressive stylization while preserving the content structure. Our experimental results demonstrate that Meta FIST achieves superior content retention, style fidelity, and adaptability compared to existing approaches.
Relation:	Electronics 2025, 14(10) p.2035
DOI:	10.3390/electronics14102035
Appears in Collections:	[Graduate Institute & Department of Computer Science and Information Engineering] Journal Article

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	4	View/Open

Loading...