北京航空航天大学学报2026，Vol.52Issue(6)：2194-2207,14.DOI:10.13700/j.bh.1001-5965.2024.0258
联合语义分割和边缘纹理的人脸图像修复
Face image inpainting combining semantic segmentation and edge texture
摘要
Abstract
Current picture inpainting techniques use auxiliary structural information prediction to fill realistic patches,however erroneous priors can result in unrealistic structures and blurry textures.Meanwhile,existing methods only focus on the relationship between the original image and the inpainted image,and do not fully utilize the information of the damaged image.To address the above problems,an end-to-end transformer face image inpainting network is proposed,which utilizes semantic segmentation and edge texture information to guide the inpainting process.The main inpainting network includes one RGB inpainting branch and two auxiliary branches for semantic segmentation and edge texture.A set of large kernel convolutional context bottleneck(LKCCB)modules is designed in the encoder to increase the effective receptive field and better contextual reasoning.In order to capture distant contextual information,a nested dynamic auxiliary normalization multi-head attention(NDAN-MHA)module is proposed,which contains a dynamic auxiliary normalization(DAN)module that can dynamically integrate the structural features of the three branches to enrich semantic consistency.Furthermore,a contrastive regularization(CR)network is proposed to stabilize and improve the training of the network to generate more realistic inpainted images.The CelebA-HQ and FFHQ datasets were used for both qualitative and quantitative trials.The findings demonstrate that the suggested method performs better than the comparative methods in both subjective and objective measures and that it can reasonably restore huge,irregularly occluded face photos.关键词
人脸图像修复/对比学习/大核卷积/注意力机制/动态辅助归一化Key words
face image inpainting/contrastive learning/large-kernel convolution/attention mechanism/dynamic auxiliary normalization分类
信息技术与安全科学引用本文复制引用
石计亮,张乾,周遵富,杨思红..联合语义分割和边缘纹理的人脸图像修复[J].北京航空航天大学学报,2026,52(6):2194-2207,14.基金项目
贵州民族大学校级科研项目(GZMUZK[2021]YB23) School-level Scientific Research Projects of Guizhou Minzu University(GZMUZK[2021]YB23) （GZMUZK[2021]YB23）
