Generating various composite human faces from real 3D facial images

Chalás, Igor; Urbanová, Petra; Juřík, Vojtěch; Ferková, Zuzana; Jandová, Marie; Sochor, Jiří­; Kozlíková, Barbora

doi:10.1007/s00371-016-1277-1

Cited by 10 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Face features are labeled from photographs so that 3D face models can be reconstructed from facial images based on face recognition. Chalás et al 15 generate character models with different appearances using a composite of facial parts from 3D scan data. However, their method needs a database of 3D scans to realize the character generation; constructing such a database for a game project is expensive.…”

Section: Related Workmentioning

confidence: 99%

Controllable automatic generation of non‐player characters in 3D anime style

Oji

Fujishiro

2022

Computer Animation & Virtual

View full text Add to dashboard Cite

Game creators always use prefabricated models as non-player characters (NPCs) to create an atmosphere for game scenes. However, players are likely to see different NPCs with the same 3D models because creators usually cannot prepare a high number of NPC models for big game scenes. In this article, we present an anime-like character customization system, where each customizing parameter can adjust the shape or color for the corresponding part of the character model. Based on this system, we propose an improved approach for generating a rich variety of 3D anime-like NPCs including body models and clothing items in different styles. We introduce a neural network to control the facial appearances, Gaussian mixture models to control the colors of hair and clothes, and a Bayesian network to control the outfits of clothing items. We demostrate that the proposed approach can maintain the variety and stability of the generated characters.

show abstract

Section: Related Workmentioning

confidence: 99%

Controllable automatic generation of non‐player characters in 3D anime style

Oji

Fujishiro

2022

Computer Animation & Virtual

View full text Add to dashboard Cite

show abstract

“…During the last two decades, three-dimensional recording has emerged as a progressive documentation technique, beneficial for a daily routine workflow in a variety of scientific fields, such as forensic sciences (Urbanová et al 2015;Urbanová et al 2017), human osteology (Ege et al 2004, Jurda andUrbanová 2016), clinical research (Šrubař et al 2015), the entertainment and game industry (Chalás et al 2017), and the humanities (Demetrescu 2015). Photo-realistic textured surface scans of the human body -acquired by technologies ranging from laser or white light scanning to passive photogrammetry to infra-red sensors -have reached a quality that allows multiple tasks (such as measurement, diagnostics, archiving, data management, and quality control) cipline, however, puts different requirements on the collected datasets.…”

Section: Introducing the Fidentis 3d Face Database Introductionmentioning

confidence: 99%

“…In addition, it has been crucial to assess pre-and post-operative status in orthodontics (Rosati et al 2010) and craniofacial surgery (Maal et al 2008, Kau et al 2006. Facial geometry also has been a subject of multiple perception studies in psychology (Atabaki et al 2015) and the entertainment industry (Chalás et al 2017. The majority of these applications are dependent on reference datasets mapping inter-or intra-population variation, including entries controlled for external conditions (e.g., expression, head position, occlusion, illumination etc.)…”

Section: Introducing the Fidentis 3d Face Database Introductionmentioning

confidence: 99%

Introducing the FIDENTIS 3D Face Database

Urbanová

Ferková

Jandová

et al. 2018

Self Cite

View full text Add to dashboard Cite

Face databases have assumed an important role in a variety of clinical and applied research domains. However, the number of datasets accessible to the scientific community is limited and the knowledge of their existence may be concealed from a wider range of specialists. In the present paper we introduce a sizeable dataset of 3D facial scans - FIDENTIS 3D Face Database (F3D-FD or FIDENTIS Database), which is accompanied by basic demographic and descriptive data. The database is structured according to recorded subjects, and comprises single-scan entries as well as a smaller number of multiscan entries. The multi-scan entries vary in the time passed between recording sessions and in the devices employed to collect the 3D data. The total number of 2476 individuals puts our database within the category of large-scale databases. The 3D scans are accessible through a web-based interface at www. fidentis.cz. A licensed version of the database is available to interested parties upon signing a license agreement. Because of its varied composition, and low target-specificity the database has capacity to be of great assistance for the worldwide research community.

show abstract

“…Chalás et al [4] present a method for automatically generating face composites. This finds its application in virtual environments where large crowds of virtual avatars may be visible and provides a straightforward manner of generating different faces via compositing facial parts from 3D scans.…”

mentioning

confidence: 99%