Effect of Training Sample on Reconstructing 3D Face Shapes from Feature Points

Online interaction with 3D facial animation is an alternative way of face-to-face communication for distance education. 3D facial modeling is essential for virtual educational environments establishment. This article presents a novel 3D facial modeling solution that facilitates quasi-facial communication for online learning. Our algorithm builds 3D facial models from a single image, with support of a 3D face database. First from the image, we extract a set of feature points, which are then used to automatically estimate the head pose parameters using the 3D mean face in our database as a reference model. After the pose recovery, a similarity measurement function is proposed to locate the neighborhood for the given image in the 3D face database. The scope of neighborhood can be determined adaptively using our cross-validation algorithm. Furthermore, the individual 3D shape is synthesized by neighborhood interpolation. Texture mapping is achieved based on feature points. The experimental results show that our algorithm can robustly produce 3D facial models from images captured in various scenarios to enhance the lifelikeness in distant learning.

Download Full-text

3D Face Reconstruction from Single 2D Image Based on Robust Facial Feature Points Extraction and Generic Wire Frame Model

2010 International Conference on Communications and Mobile Computing ◽

10.1109/cmc.2010.151 ◽

2010 ◽

Cited By ~ 7

Author(s):

Xiaojiu Fan ◽

Qiang Peng ◽

Ming Zhong

Keyword(s):

Facial Feature ◽

Feature Points ◽

3D Face Reconstruction ◽

3D Face ◽

Frame Model ◽

Face Reconstruction ◽

Wire Frame

Download Full-text

Fast Modelling Algorithm for Realistic Three-Dimensional Human Face for Film and Television Animation

Complexity ◽

10.1155/2021/3346136 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Limin Xu

Keyword(s):

Three Dimensional ◽

Reconstruction Method ◽

Feature Points ◽

Human Face ◽

3D Face Reconstruction ◽

3D Face ◽

Film And Television ◽

Face Reconstruction ◽

Reconstruction Performance ◽

The Face

Aiming at the face photos of film and television animation, this paper proposes a new fast three-dimensional (3D) face modelling algorithm. First of all, based on the LBF algorithm, this paper proposes a multifeature selection idea to automatically detect multiple features of the face. Secondly, in order to solve the shortcomings of slow training speed while achieving large pose face alignment, the regression-based CNN is selected as the algorithm to achieve fast convergence. Then, due to the influence of various factors, the extracted feature points are not completely correct, and Gabor features are used to screen the matching of feature points. Finally, by analysing the principle of 3DMM 3D face reconstruction, a single-view 3D face reconstruction method based on CNN is proposed. The experimental results show that the algorithm in this paper has good reconstruction performance and real-time performance and can realize the rapid modelling of human face.

Download Full-text

Quasi-Facial Communication for Online Learning Using 3D Modeling Techniques

Web-Based Education ◽

10.4018/978-1-61520-963-7.ch049 ◽

2010 ◽

pp. 727-737

Author(s):

Yushun Wang ◽

Yueting Zhuang

Keyword(s):

Online Learning ◽

Reference Model ◽

Texture Mapping ◽

Feature Points ◽

Face Database ◽

3D Face ◽

Distant Learning ◽

Facial Modeling ◽

The Individual ◽

3D Face Database

Online interaction with 3D facial animation is an alternative way of face-to-face communication for distance education. 3D facial modeling is essential for virtual educational environments establishment. This article presents a novel 3D facial modeling solution that facilitates quasi-facialcommunication for online learning. Our algorithm builds 3D facial models from a single image, with support of a 3D face database. First from the image, we extract a set of feature points, which are then used to automatically estimate the head pose parameters using the 3D mean face in our database as a reference model. After the pose recovery, a similarity measurement function is proposed to locate the neighborhood for the given image in the 3D face database. The scope of neighborhood can be determined adaptivelyusing our cross-validation algorithm. Furthermore, the individual 3D shape is synthesized by neighborhood interpolation. Texture mapping is achieved based on feature points. The experimental results show that our algorithm can robustly produce 3D facial models from images captured in various scenarios to enhance the lifelikeness in distant learning.

Download Full-text