计算机应用研究2024，Vol.41Issue(10)：3183-3187,5.DOI:10.19734/j.issn.1001-3695.2023.12.0598
NFP-AST:自然特征保留的任意风格迁移模型
NFP-AST:arbitrary style transfer model for natural feature preservation
摘要
Abstract
The extraction of affinity features and natural fusion are crucial for achieving style transfer.To address this prob-lem,this paper proposed a novel arbitrary style transfer model,called NFP-AST,emphasizing the preservation of natural fea-tures.Through a reversible residual network,it performed binary processing of features in both forward and backward infe-rences,ensuring the extraction of affinity features and reducing image reconstruction errors.In the adaptive space reconstruc-tion module(ASRM),it firstly used global statistical information to match content and style features,followed by interpolating adaptive weights in the fusion features to capture details for unbiased merging of content and style features,resulting in a natu-ral style transition.Qualitative and quantitative experimental results indicate that NFP-AST produces stylized images with bet-ter scores compared to state-of-the-art methods,demonstrating enhanced visual impact in artistic expression.关键词
自然特征保留/可逆残差网络/特征亲和性/自适应空间重构/无偏融合Key words
natural feature preservation/reversible residual network/feature affinity/adaptive spatial reconstruction/unbiased fusion分类
信息技术与安全科学引用本文复制引用
赵敏,钱雪忠,宋威..NFP-AST:自然特征保留的任意风格迁移模型[J].计算机应用研究,2024,41(10):3183-3187,5.基金项目
国家自然科学基金项目(62076110) （62076110）
江苏省自然科学基金项目(BK20181341) （BK20181341）
