Reversible Network with Meta ActNorm for Content-Preserved Image Style Transfer
學年 113
學期 2
發表日期 2025-06-24
作品名稱 Reversible Network with Meta ActNorm for Content-Preserved Image Style Transfer
作品名稱(其他語言)
著者 Hwei-Jen Lin and Kai-Jun Lin
作品所屬單位
出版者
會議名稱 International Conference on Computer, Communication and Information Sciences, and Engineering
會議地點 Vancouver, Canada
摘要 This study focuses on image style transfer techniques and presents improvements to the ArtFlow framework proposed by Jie An et al.. ArtFlow employs a reversible mechanism that maps an image from the pixel space to the feature space during the forward process, transforming it into a feature vector. A style transfer module then converts this feature vector into a stylized one. In the reverse process, the stylized feature vector is mapped back to the pixel space to obtain the final stylized image, effectively preserving the original content details. This reversible design helps prevent content leakage, a common issue in traditional methods. However, there remains room for improvement in terms of adaptability. To enhance the model's adaptability while maintaining structural fidelity, this paper modifies the core activation normalization mechanism within the ArtFlow framework and proposes a novel normalization approach. Inspired by the concept of "learning to learn" in meta-learning, we introduce Meta Activation Normalization (Meta-Actnorm). The improved architecture is termed the Multi-Block Adaptive Flow (MBAF) model. In the MBAF model, Meta-Actnorm dynamically adjusts normalization parameters based on the input image during the forward process and effectively integrates these parameters during the reverse process, further enhancing the model’s adaptability and stability. A series of experiments and quantitative evaluations demonstrate that the proposed method not only preserves key structures and details of the content image but also ensures visual consistency after style transfer, avoiding distortions such as structural deformation.
關鍵字 arbitrary image style transfer, flow model, content leaking, meta active normalization
語言 en_US
收錄於
會議性質 國際
校內研討會地點
研討會時間 20250624~20250625
通訊作者
國別 CAN
公開徵稿
出版型式
出處