A method of face texture fusion based on visibility weight

一种基于可见性权重的人脸纹理融合方法

¹ School of Electronics and Information, Northwestern Polytechnical University, Xi'an 710072, China
² Content Production Center of Virtual Reality, Beijing 101318, China

Received: 23 May 2022

Abstract

In the reconstruction process from 2D images to 3D face models, texture completion still suffers from pixel blurring and color inconsistency when face images are under different perspectives. In this paper, we propose a method based on visibility weights for face texture fusion. Meanwhile, for the complex geometric structure of the ear region where the traditional texture mapping algorithm is inapplicable, a skin color probability method with Gaussian model is used for pixel completion, and jointly optimized with the texture fusion band. Finally, we generate a complete and high-fidelity face texture model. The simulation experiment shows that the novel face texture fusion and completion method generates the perfect texture under multiple viewpoints. Our face texture model outperforms state-of-the-art techniques under the same rendering conditions.

摘要

由二维图像到三维人脸模型的重建过程中, 不同角度下的人脸在进行纹理补全时, 存在纹理像素模糊和亮度差异的问题, 提出一种基于可见性权重的方法, 对于不同视角下的人脸纹理图进行融合。同时, 针对耳部区域结构复杂, 传统纹理融合算法不适用的情况, 利用高斯模型的肤色概率方法对耳部纹理缺失区域进行补全, 并设计纹理融合带平滑像素, 最终得到完整、逼真度较高的人脸纹理模型。仿真实验结果表明, 所提人脸纹理融合与补全方法实现了多角度下头面部区域纹理的完美融合。与目前通用的方法相比较, 在同样的渲染条件下, 所提方法生成的人脸纹理模型更完整、纹理显示效果更好。