An Automatic Dense Point Registration Method for 3D Face Animation

2009 ◽  
Author(s):  
Yongli Hu ◽  
Mingquan Zhou ◽  
Zhongke Wu
Keyword(s):  
Registration Method ◽  
3D Face ◽  
Face Animation ◽  
Dense Point

3D Face Recognition Based on Regional Shape Maps

2018 ◽  
Vol 22 (1) ◽  
pp. 141-146 ◽  
Author(s):  
Xiaoni Wang ◽  
Keyword(s):  
Face Recognition ◽  
Recognition Performance ◽  
3D Face Recognition ◽  
Face Database ◽  
Registration Method ◽  
3D Face ◽  
Feature Vectors ◽  
Input Face ◽  
Point To Point ◽  
3D Face Database

This study proposes an iterative closest shape point (ICSP) registration method based on regional shape maps for 3D face recognition. A neutral expression image randomly selected from a face database is considered as the reference face. The point-to-point correspondences between the input face and the reference face are achieved by constructing the points’ regional shape maps. The distance between corresponding point pairs is then minimized by iterating through the correspondence findings and coordinate transformations. The vectors composed of the closest shape points obtained in the last iteration are regarded as the feature vectors of the input face. These 3D face feature vectors are finally used for both training and recognition using the Fisherface method. Experiments are conducted using the 3D face database maintained by the Chinese Academy of Science Institute of Automation (CASIA). The results show that the proposed method can effectively improve 3D face recognition performance.

scholarly journals A REGISTRATION METHOD OF POINT CLOUDS COLLECTED BY MOBILE LIDAR USING SOLELY STANDARD LAS FILES INFORMATION

2017 ◽  
Vol XLII-1/W1 ◽  
pp. 121-128 ◽  
Author(s):  
L. Gézero ◽  
C. Antunes
Keyword(s):  
Point Cloud ◽  
Large Scale ◽  
Auxiliary Information ◽  
Point Clouds ◽  
Registration Method ◽  
Digital Terrain ◽  
Terrain Models ◽  
Dense Point ◽  
Fully Automatic ◽  
Method Point

In the last few years, LiDAR sensors installed in terrestrial vehicles have been revealed as an efficient method to collect very dense 3D georeferenced information. The possibility of creating very dense point clouds representing the surface surrounding the sensor, at a given moment, in a very fast, detailed and easy way, shows the potential of this technology to be used for cartography and digital terrain models production in large scale. However, there are still some limitations associated with the use of this technology. When several acquisitions of the same area with the same device, are made, differences between the clouds can be observed. The range of that differences can go from few centimetres to some several tens of centimetres, mainly in urban and high vegetation areas where the occultation of the GNSS system introduces a degradation of the georeferenced trajectory. Along this article a different method point cloud registration is proposed. In addition to the efficiency and speed of execution, the main advantages of the method are related to the fact that the adjustment is continuously made over the trajectory, based on the GPS time. The process is fully automatic and only information recorded in the standard LAS files is used, without the need for any auxiliary information, in particular regarding the trajectory.

Learning 3D Face Deformation Model

2011 ◽  
pp. 317-340
Author(s):  
Zhen Wen ◽  
Pengyu Hong ◽  
Jilin Tu ◽  
Thomas S. Huang
Keyword(s):  
Motion Analysis ◽  
Deformation Model ◽  
Interpolation Scheme ◽  
Unified Framework ◽  
3D Face ◽  
Facial Motion ◽  
Face Animation ◽  
Mesh Topology ◽  
Modeling Analysis ◽  
Analysis And Synthesis

This chapter presents a unified framework for machine-learning-based facial deformation modeling, analysis and synthesis. It enables flexible, robust face motion analysis and natural synthesis, based on a compact face motion model learned from motion capture data. This model, called Motion Units (Muss), captures the characteristics of real facial motion. The MU space can be used to constrain noisy low-level motion estimation for robust facial motion analysis. For synthesis, a face model can be deformed by adjusting the weights of Mus. The weights can also be used as visual features to learn audio-to-visual mapping using neural networks for real-time, speech-driven, 3D face animation. Moreover, the framework includes parts-based MUs because of the local facial motion and an interpolation scheme to adapt MUs to arbitrary face geometry and mesh topology. Experiments show we can achieve natural face animation and robust non-rigid face tracking in our framework.

scholarly journals Super Edge 4-Points Congruent Sets-Based Point Cloud Global Registration

2021 ◽  
Vol 13 (16) ◽  
pp. 3210
Author(s):  
Shikun Li ◽  
Ruodan Lu ◽  
Jianya Liu ◽  
Liang Guo
Keyword(s):  
Three Dimensional ◽  
Initial Point ◽  
Point Clouds ◽  
Search Space ◽  
Frame Rate ◽  
Registration Method ◽  
Dense Point ◽  
Coarse Registration ◽  
Fine Registration ◽  
Original Point

With the acceleration in three-dimensional (3D) high-frame-rate sensing technologies, dense point clouds collected from multiple standpoints pose a great challenge for the accuracy and efficiency of registration. The combination of coarse registration and fine registration has been extensively promoted. Unlike the requirement of small movements between scan pairs in fine registration, coarse registration can match scans with arbitrary initial poses. The state-of-the-art coarse methods, Super 4-Points Congruent Sets algorithm based on the 4-Points Congruent Sets, improves the speed of registration to a linear order via smart indexing. However, the lack of reduction in the scale of original point clouds limits the application. Besides, the coplanarity of registration bases prevents further reduction of search space. This paper proposes a novel registration method called the Super Edge 4-Points Congruent Sets to address the above problems. The proposed algorithm follows a three-step procedure, including boundary segmentation, overlapping regions extraction, and bases selection. Firstly, an improved method based on vector angle is used to segment the original point clouds aiming to thin out the scale of the initial point clouds. Furthermore, overlapping regions extraction is executed to find out the overlapping regions on the contour. Finally, the proposed method selects registration bases conforming to the distance constraints from the candidate set without consideration about coplanarity. Experiments on various datasets with different characteristics have demonstrated that the average time complexity of the proposed algorithm is improved by 89.76%, and the accuracy is improved by 5 mm on average than the Super 4-Points Congruent Sets algorithm. More encouragingly, the experimental results show that the proposed algorithm can be applied to various restrictive cases, such as few overlapping regions and massive noise. Therefore, the algorithm proposed in this paper is a faster and more robust method than Super 4-Points Congruent Sets under the guarantee of the promised quality.

Learning 3D Face-Animation Model

2005 ◽  
pp. 1807-1814
Author(s):  
Zhen Wen ◽  
Pengyu Hong ◽  
Jilin Tu ◽  
Thomas S. Huang
Keyword(s):  
Virtual Environments ◽  
Human Face ◽  
3D Face ◽  
Face Animation ◽  
Computer Aided ◽  
Synthetic Agents

A synthetic human face is useful for visualizing information related to the human face. The applications include visual telecommunication (Aizawa & Huang, 1995), virtual environments and synthetic agents (Pandzic, Ostermann, & Millen, 1999), and computer-aided education.

Sign in / Sign up

Export Citation Format

Share Document