RETRACTED ARTICLE: Three-dimensional face
         reconstruction of static images and computer standardization issues

Zhao, Hongjun; Wu, Bin

doi:10.1007/s00500-021-05999-5

Cited by 4 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhao et al introduced a facial manipulation-based 3D facial reconstruction method focusing on improving the accuracy and usefulness of the reconstruction [43]. Wu et al explored the methodology of 3D facial reconstruction from static images and the issues related to computer standardisation [44].…”

Section: ) Face Expression Migrationmentioning

confidence: 99%

Virtual Human: A Comprehensive Survey on Academic and Applications

Cui,

Liu

2023

IEEE Access

View full text Add to dashboard Cite

As a creative method for virtual human individuals based on multiple fusion technologies such as artificial intelligence, computer graphics, and speech synthesis, virtual human technology has developed rapidly since its birth, and continuous discussions and studies have been conducted in both academia and industry. Starting from the film and television industries, the cross-disciplinary application of virtual human has been continuously recognized and applied in fields such as media, games, and finance. Although virtual human has achieved sufficient development and innovation, it faces many challenges such as emotion recognition, privacy, and security, as well as the uncanny valley effect. This article starts with the development history of virtual human and analyzes the current academic research status and application scenarios in combination with the characteristics, technical architecture, and application of virtual human technology. At the same time, this article sorts out seven mainstream application scenarios of virtual human and analyzes their main advantages and possible future challenges. This article provides a valuable reference for subsequent related research by exploring development trends, application fields, and future research trends in virtual human.

show abstract

Section: ) Face Expression Migrationmentioning

confidence: 99%

Virtual Human: A Comprehensive Survey on Academic and Applications

Cui,

Liu

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Moreover, these methods typically employ complex network architectures, resulting in a multitude of parameters and sluggish loading speeds. Consequently, when the necessity arises to create a 3D expression, scholars typically employ a process of 3D reconstruction from 2D images [22,23]. However, the quality of such reconstructions is significantly influenced by factors such as image noise, lighting conditions, and the camera's point of view.…”

Section: Introductionmentioning

confidence: 99%

Neutral Facial Rigging from Limited Spatiotemporal Meshes

Hou,

Weng,

Zhao

et al. 2024

Electronics

View full text Add to dashboard Cite

Manual facial rigging is time-consuming. Traditional automatic rigging methods lack either 3D datasets or explainable semantic parameters, which makes it difficult to retarget a certain 3D expression to a new face. To address the problem, we automatically generate a large 3D dataset containing semantic parameters, joint positions, and vertex positions from a limited number of spatiotemporal meshes. We establish an expression generator based on a multilayer perceptron with vertex constraints from the semantic parameters to the joint positions and establish an expression recognizer based on a generative adversarial structure from the joint positions to the semantic parameters. To enhance the accuracy of key facial area recognition, we add local vertex constraints for the eyes and lips, which are determined by the 3D masks computed by the proposed projection-searching algorithm. We testthe generation and recognition effects on a limited number of publicly available Metahuman meshes and self-collected meshes. Compared with existing methods, our generator has the shortest generation time of 14.78 ms and the smallest vertex relative mean square error of 1.57 × 10−3, while our recognizer has the highest accuracy of 92.92%. The ablation experiment verifies that the local constraints can improve the recognition accuracy by 3.02%. Compared with other 3D mask selection methods, the recognition accuracy is improved by 1.03%. In addition, our method shows robust results for meshes of different levels of detail, and the rig has more dimensions of semantic space. The source code will be made available if this paper is accepted for publication.

show abstract

“…The concepts upon which a 3D morphable face model is based allow it to generate an accurate representation of a human face, which offers the finest possible collection of data progression in framework for 3D facial recognition and reconstruction (FFRR) by: beginning with a collection of example faces, a registration approach establishes dense point-to-point relationship between all faces and then keeps it that way throughout the rest of the processing steps. 3D morphable model (3DMM) is also used in the facial reconstruction process, which reconstructs the shape and size of faces 9 . 3DMM models boost the precision of the facial reproduction procedure, enhancing accuracy.…”

Section: Introductionmentioning

confidence: 99%

Framework for facial recognition and reconstruction for enhanced security and surveillance monitoring using 3D computer vision

Wang

Zhang

2023

J. Electron. Imag.

View full text Add to dashboard Cite

Workflows can be optimized with the use of three-dimensional (3D) computer vision (CV) by monitoring processes from many angles. The potential for increased efficiency and cost savings is clear here. Input scenarios are always being monitored by security and surveillance systems to recognize and classify items, human faces, and moving things. The input reconstruction in these surveillance systems is problematic because of the mapping from three dimensions to two dimensions in the form of pixels. We present a new 3D CV paradigm-based framework for facial recognition and reconstruction. In this setup, deep neural networks are used to distinguish between mapped and unmapped pixels during a 2D to 3D or 3D to 2D transformation. To use correlation analysis to recognize human faces, it is necessary to first examine the input image for textural properties. The mapping procedure continues with the extraction of textural elements using dimensional contours. Then, continuous contours are used to do the 3D mapping and reduce the number of false positives. Instead, this framework isolates individual contours of moving objects or faces to increase the number of training iterations. Finally, missing pixels in the dimension conversion are filled to rebuild the human face utilizing discrete and continuous outlines. Hence, the suggested framework minimizes the false rate (10%), increases the false positive rate as (13.93%), and minimizes the error by (9.89%) while maximizing the recognition accuracy for (13.93%) and the precision is (13.21%).

show abstract

RETRACTED ARTICLE: Three-dimensional face reconstruction of static images and computer standardization issues

Cited by 4 publications

References 25 publications

Virtual Human: A Comprehensive Survey on Academic and Applications

Virtual Human: A Comprehensive Survey on Academic and Applications

Neutral Facial Rigging from Limited Spatiotemporal Meshes

Framework for facial recognition and reconstruction for enhanced security and surveillance monitoring using 3D computer vision

Contact Info

Product

Resources

About