高分辨率人脸纹理图全流程生成方法
Full process generation method of high-resolution face texture map
朱宝旭 1刘漫丹 1张雯婷 1谢立志1
作者信息
- 1. 华东理工大学能源化工过程智能制造教育部重点实验室,上海 200237
- 折叠
摘要
针对人脸纹理生成相关研究大部分聚焦于低分辨率纹理生成的问题,将图像翻译运用到高分辨率纹理图的生成中,提出一种以图像翻译网络为核心的1024×1024纹理图的全流程生成方法.在快速高效生成的同时,有效缓解了生成人脸UV纹理分辨率低的问题.在图像翻译网络中,由卷积神经网络作为骨干网络,嵌入统计纹理学习网络(STLNet),并采用软自适应层实例规范化(Soft-AdaLIN)的归一化方法共同构成生成器,同时采用多尺度判别来指导高分辨率纹理图像的生成,最后进行颜色转换与泊松融合完成纹理校正.在FFHQ数据集随机抽取图像并进行人脸归一化后进行测试,通过一系列评价指标进行定量评估、同近年相关研究方法进行定性及定量比较,验证了该全流程生成方法在生成1024×1024人脸UV纹理图像上的优势.
Abstract
Most research on face texture generation focuses on low-resolution generation.To address this,the image translation was applied to the generation of high-resolution texture maps,proposing a whole-process method for generating 1024*1024 texture maps using an image translation network as the main part.This method effectively alleviated the problem of low resolution of ultraviolet texture generation,while ensuring rapid and efficient generation.In the image translation network,the convolutional neural networks served as the backbone network,combined with the statistical texture learning network(STLNet)and the normalization method of soft adaptive layer-instance normalization(Soft-AdaLIN)to form the generator.Meanwhile,multi-scale discrimination was employed to guide the generation of high-resolution texture images,and finally color conversion and Poisson fusion were performed to complete texture correction.Images were randomly extracted from the FFHQ dataset for face normalization and tested.Through a series of evaluation indexes for quantitative evaluation,qualitative and quantitative comparisons with recent relevant research methods,the advantages of this whole-process generation method in generating 1024×1024 face UV texture images were verified.
关键词
人脸图像翻译/人脸纹理图/高分辨率/生成对抗网络/统计纹理学习/纹理映射Key words
face image translation/face texture map/high resolution/generative adversarial network/statistical texture learning/texture mapping引用本文复制引用
基金项目
中央高校基本科研业务费专项资金资助项目(222201917006)
出版年
2024
NETL
NSTL
万方数据