• 한국컴퓨터그래픽스학회논문지
• /
• 제22권2호
• /
• pp.11-19
• /
• 2016

본 논문은 페이셜 캡처 데이터로부터 페이셜 리그에 대한 다이렉트 리타겟팅을 수행하는 새로운 방법론에 대하여 다룬다. 페이셜 리그는 프로덕션 파이프라인에서 아티스트가 손쉽게 페이셜 애니메이션을 제작하기 위하여 만들어진 제작도구로서, 모션 캡처 등으로 생성된 얼굴 애니메이션 데이터를 페이셜 리그에 매핑할 경우 아티스트에게 친숙한 방식으로 손쉽게 수정, 편집할 수 있으므로 작업 능률을 크게 향상시킬 수 있다는 장점이 있다. 그러나, 페이셜 리그는 그 종류와 작동 방식이 매우 다양하므로, 다양한 페이셜 리그에 대하여 강건하고 안정적으로 모션 데이터를 매핑할 수 있는 일반화된 방법을 찾기는 쉽지 않다. 이를 위하여, 본 논문은 캡처된 얼굴 모션 중 몇 개의 대표적 표정에 대하여 아티스트가 페이셜 리그로 제작한 표정을 예제로 학습시키는 데이터 기반 페이셜 리타겟팅 방식을 제안한다. 이를 통하여 우리는 아티스트가 페이셜 캡처 데이터를 기존 애니메이션 파이프라인의 페이셜 리그를 활용하여 손쉽게 수정할 수 있도록 할 뿐 아니라, 수십 수백개의 대응점을 일일이 지정해 주어야 하거나 사람과 많이 다른 동물 및 괴물 형태의 얼굴에는 리타겟팅이 잘 이루어지지 않았던 기존 대응점 기반 리타겟팅 방식의 한계점 또한 극복할 수 있었다. 본 논문의 결과물들은 우리의 방식이 제공하는 단순하면서도 직관적인 얼굴 애니메이션 리타겟팅이 실제 애니메이션 프로덕션에서 얼마나 효율적으로 활용될 수 있는지를 보여준다.

• 한국멀티미디어학회논문지
• /
• 제24권9호
• /
• pp.1279-1284
• /
• 2021

This paper addresses the task of transferring facial blendshape models to an arbitrary target face. Blendshape is a common method for the facial rig; however, production of blendshape rig is a time-consuming process in the current facial animation pipeline. We propose automatic blendshape facial rigging based on our blendshape transfer method. Our method computes the difference between source and target facial model and then transfers the source blendshape to the target face based on a deformation transfer algorithm. Our automatic method provides efficient production of a controllable digital human face; the results can be applied to various applications such as games, VR chating, and AI agent services.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권3호
• /
• pp.56-63
• /
• 2020

The Avengers film produced by Marvel Comics shows visual effects that were impossible to produce in the past. Companies that produce film special effects were initially equipped with large personnel and equipment, but technology is gradually evolving to be feasible for smaller companies that do not have high-priced equipment and a large workforce. The development of hardware and software is becoming increasingly available to the general public as well as to experts. Equipment and software which were difficult for individuals to purchase before quickly popularized high-performance computers as the game industry developed. The development of the cloud has been the driving force behind software costs. As augmented reality (AR) performance of mobile devices improves, advanced technologies such as motion tracking and face recognition technology are no longer implemented by expensive equipment. Under these circumstances, after implementing mobile-based facial capture technology in animation projects, we have identified the pros and the cons and suggest better solutions to improve the problem.

• International journal of advanced smart convergence
• /
• 제8권2호
• /
• pp.162-169
• /
• 2019

Facial rigging technology has been developing more and more since the 21st century. Facial rigging of various methods is still attempted and a technique of capturing the geometry in real time recently also appears. Currently Modern CG is produced image which is hard to distinguish from actual photograph. However, this kind of technology still requires a lot of equipment and cost. The purpose of this study is to perform facial rigging using muscle simulation instead of using such equipment. Original muscle simulations were made primarily for use in the body of a creature. In this study, however, we use muscle simulations for facial rigging to create a more realistic creature-like effect. To do this, we used Ziva Dynamics' Ziva VFX muscle simulation software. We also develop a method to overcome the disadvantages of muscle simulation. Muscle simulation can not be applied in real time and it takes time to simulate. It also takes a long time to work because the complex muscles must be connected. Our study have solved this problem using blendshape and we want to show you how to apply our method to face rig.

• Safety and Health at Work
• /
• 제10권3호
• /
• pp.275-304
• /
• 2019

Background: Air-purifying, tight-fitting facepieces are examples of respiratory protective equipment and are worn to protect workers from potentially harmful particulate and vapors. Research shows that the presence of facial hair on users' face significantly reduces the efficacy of these devices. This article sets out to establish if an acceptable seal could be achieved between facial hair and the facepiece. The team also created and investigated a low-cost "pressure testing" method for assessing the efficacy of a seal to be used during the early design process for a facepiece designed to overcome the facial hair issue. Methods: Nine new designs for face mask seals were prototyped as flat samples. A researcher developed a test rig, and a test protocol was used to evaluate the efficacy of the new seal designs against facial hair. Six of the seal designs were also tested using a version of the conventional fit test. The results were compared with those of the researcher-developed test to look for a correlation between the two test methods. Results: None of the seals performed any better against facial hair than a typical, commercially available facepiece. The pressure testing method devised by the researchers performed well but was not as robust as the fit factor testing. Conclusion: The results show that sealing against facial hair is extremely problematic unless an excessive force is applied to the facepiece's seal area pushing it against the face. The means of pressure testing devised by the researchers could be seen as a low-cost technique to be used at the early stages of a the design process, before fit testing is viable.