摘要
针对现有的任意风格迁移模型无法平衡生成图像中风格信息和内容信息的问题,本文提出一种改进的任意风格迁移模型。该模型在实施风格转化前整合了一个多尺度语义调整模块。此模块通过对风格特征映射和内容特征映射进行深度语义调整,强化关键特征表达,以改善风格迁移后图像内容结构与风格特征难以协调的问题。另外,本文还提出一种语义调整损失函数,旨在使网络能更精确地保留原始图像的内容结构,并更加细腻地迁移目标风格图片的风格信息。实验结果表明,本文所提出的方法在较好地保留图片内容信息的基础上,进一步提升了风格信息的迁移效果。
Addressing the challenge of balancing style and content information in existing arbitrary style transfer models,this paper introduces an improved model for arbitrary style transfer.The model incorporates a multi-scale semantic adjustment module before the style transformation process.This module deeply adjusts style and content feature mappings to enhance key feature expressions,improving the coherence of image content structure and style features after style transfer.Additionally,a semantic adjustment loss function is proposed to precisely preserve the original image’s content structure and delicately transfer the target style’s features.The experimental results show that this method not only maintains the content information but also enhances the style transfer effects.
作者
祝露露
谷林
ZHU Lulu;GU Lin(School of Computer Science,Xi’an Polytechnic University,Xi’an 710699,China)
出处
《计算机与现代化》
2025年第9期73-78,89,共7页
Computer and Modernization
关键词
任意风格迁移
多尺度语义调整
强化关键特征表达
语义调整损失函数
arbitrary style transfer
multi-scale semantic adjustment
enhance key feature expressions
semantic adjustment loss
