Special Issues
Table of Content

Beyond the Surface: Exploring the Depths of Deep Learning in Face Recognition

Submission Deadline: 01 June 2025 (closed) View: 769

Guest Editors

Prof. Dr. Soo Kyun Kim

Email: kimsk@jejunu.ac.kr

Affiliation: Department of Computer Engineering, Jeju National University, Jeju, 63243, South Korea.

Homepage:  https://ce.jejunu.ac.kr/ce/professor/professorinfo.htm

Research Interests: Facial Expressions, 3D Reconstruction, Graph Attention Network, Graph Neural Networks

图片1.png


Prof. Dr. Min Hong

Email: mhong@sch.ac.kr

Affiliation: Computer Software Engineering, Soonchunhyang University, Asan-si, 31538, South Korea.

Homepage:

Research Interests: physically-based modeling and simulation, bioinformatics, and image processing related applications

图片2.png


Summary

This special issue delves into the cutting-edge technology of three-dimensional (3D) facial reconstruction, which generates a 3D model of a face by estimating its shape and structure from a two-dimensional (2D) image. This technique significantly enhances workflows and improves output quality in various fields such as computer vision, graphic design, game development, and film technology. Creating lifelike virtual characters with realistic faces in virtual reality (VR) or augmented reality (AR) and enhancing the realism of gaming characters are crucial objectives. The 3D facial reconstruction technique enables detailed facial expressions, emotions, and lip movements in virtual characters, thereby increasing their believability and realism.


Both original research and reviews will be considered. The following subtopics are the particular interests of this special issue, including but not limited to:

1) Advanced Techniques in 3D Facial Reconstruction from 2D Images

2) Integrating Multi-Modal Data for Robust 3D Facial Reconstruction

3) Enhancing Realism in Virtual Characters

 



Keywords

Facial Expressions, 3D Reconstruction, Graph Attention Network, Applications in VR/AR environments and interactive media, Hybrid Neural Network Architectures

Published Papers


  • Open Access

    ARTICLE

    A Novel Face-to-Skull Prediction Based on Face-to-Back Head Relation

    Tien-Tuan Dao, Lan-Nhi Tran-Ngoc, Trong-Pham Nguyen-Huu, Khanh-Linh Dinh-Bui, Nhat-Minh Nguyen, Ngoc-Bich Le, Tan-Nhu Nguyen
    CMC-Computers, Materials & Continua, Vol.84, No.2, pp. 3345-3369, 2025, DOI:10.32604/cmc.2025.065279
    (This article belongs to the Special Issue: Beyond the Surface: Exploring the Depths of Deep Learning in Face Recognition)
    Abstract Skull structures are important for biomechanical head simulations, but they are mostly reconstructed from medical images. These reconstruction methods harm the human body and have a long processing time. Currently, skull structures can be straightforwardly predicted from the head, but a full head shape must be available. Most scanning devices can only capture the face shape. Consequently, a method that can quickly predict the full skull structures from the face is necessary. In this study, a novel face-to-skull prediction procedure is introduced. Given a three-dimensional (3-D) face shape, a skull mesh could be predicted so… More >

Share Link