一种基于可见性权重的人脸纹理融合方法

Yang Liu, Yangyu Fan, Haoyue Ma, Guoyun Lyu, Shiya Liu

科研成果: 期刊稿件文章同行评审

摘要

In the reconstruction process from 2D images to 3D face models, texture completion still suffers from pix- el 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 gener- ate a complete and high-fidelity face texture model. The simulation experiment shows that the novel face texture fu- sion and completion method generates the perfect texture under multiple viewpoints. Our face texture model outper- forms state-of-the-art techniques under the same rendering conditions.

投稿的翻译标题A method of face texture fusion based on visibility weight
源语言繁体中文
页(从-至)370-378
页数9
期刊Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University
41
2
DOI
出版状态已出版 - 4月 2023

关键词

  • face reconstruction
  • face texture completion
  • face texture mapping
  • texture fusion

指纹

探究 '一种基于可见性权重的人脸纹理融合方法' 的科研主题。它们共同构成独一无二的指纹。

引用此