计算机应用与软件2024，Vol.41Issue(8)：266-270,318,6.DOI:10.3969/j.issn.1000-386x.2024.08.038
一种基于自注意力机制的人脸图像补全算法
A FACE IMAGE INPAINTING ALGORITHM BASED ON SELF ATTENTION MECHANISM
杨博文 1何衡湘 1邓洪峰1
作者信息
- 1. 西南技术物理研究所 四川成都 610000
- 折叠
摘要
Abstract
In the application of current deep learning methods in large area information missing face image inpainting,the inpainting results show issues such as blurred texture details,structural deformation,and distortion.Aimed at these problems,an image inpainting algorithm based on self-attention mechanism is proposed.The image to be completed was input into the rough generation network based on skip-connection to get the preliminary repair.The initial results were input into the self-attention sensing branch and the hybrid hole convolution branch to encode together,and the generated results were obtained by decoding.The dual discriminant was used to optimize the discriminant.Through the experiments and tests on face image CelebA-HQ dataset,the results show that the proposed method has better inpainting effect than the deep fill and PLC algorithms in objective and subjective evaluation.关键词
图像补全/生成对抗网络/跳跃连接/自注意力机制/混合空洞卷积Key words
Image inpainting/Generative adversarial network/Skip-connection/Self attention/Hybrid dilated convolution分类
信息技术与安全科学引用本文复制引用
杨博文,何衡湘,邓洪峰..一种基于自注意力机制的人脸图像补全算法[J].计算机应用与软件,2024,41(8):266-270,318,6.
