• International Journal of Internet, Broadcasting and Communication
• /
• 제16권3호
• /
• pp.113-120
• /
• 2024

Recently, case presentations using AI functions such as ChatGPT are increasing in many industrial fields. As AI-based results emerge even in the areas of images and videos, traditional animation production tools are in need of significant changes. Unreal Engine is the tool that adapts most quickly to these changes, proposing a new animation production workflow by integrating tools such as Metahuman and Marvelous Designer. Working with realistic metahumans allows for the production of realistic and natural movements, such as those captured through motion capture data. Implementing this approach presents many challenges for production tools that adhere to traditional methods. In this study, we investigated the differences between the cell animation workflow and the computer graphics animation production workflow. We compared and analyzed whether these differences could be reduced by creating sample movements using character rigs in Maya and Cascadeur tools. Our results showed that a similar cell animation workflow could be constructed using the Cascadeur tool. To improve the accuracy of our conclusions, we created large, action-packed short animations to demonstrate and validate our findings.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.286-292
• /
• 2023

This article is set against the backdrop of the rapid development of the metaverse and artificial intelligence technologies, and aims to explore the possibility and potential impact of integrating AI technology into the traditional 3D animation production process. Through an in-depth analysis of the differences when merging traditional production processes with AI technology, it aims to summarize a new innovative workflow for 3D animation production. This new process takes full advantage of the efficiency and intelligent features of AI technology, significantly improving the efficiency of animation production and enhancing the overall quality of the animations. Furthermore, the paper delves into the creative methods and developmental implications of artificial intelligence technology in real-time rendering engines for 3D animation. It highlights the importance of these technologies in driving innovation and optimizing workflows in the field of animation production, showcasing how they provide new perspectives and possibilities for the future development of the animation industry.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.91.5-91
• /
• 2002

$\textbullet$ Visualization $\textbullet$ Animation $\textbullet$ Simulation $\textbullet$ Software Components $\textbullet$ Workflow Management

• International journal of advanced smart convergence
• /
• 제12권1호
• /
• pp.130-139
• /
• 2023

With the increasing popularity of computer-generated virtual influencers, the trend is rising especially on social media. Famous virtual influencer characters Lil Miquela and Imma were all created by CGI graphics workflows. The process is typically a linear affair. Iteration is challenging and costly. Development efforts are frequently siloed off from one another. Moreover, it does not provide a real-time interactive experience. In the previous study, a real-time graphic workflow was proposed for the Digital Actor Hologram project while the output graphic quality is less than the results obtained from the CGI graphic workflow. Therefore, a real-time engine graphic workflow for Virtual Influencers is proposed in this paper to facilitate the creation of real-time interactive functions and realistic graphic quality. The real-time graphic workflow is obtained from four processes: Facial Modeling, Facial Texture, Material Shader, and Look-Development. The analysis of performance with real-time graphical workflow for Digital Actor Hologram demonstrates the usefulness of this research result. Our research will be efficient in producing virtual influencers.

• Journal of information and communication convergence engineering
• /
• 제21권2호
• /
• pp.152-158
• /
• 2023

In recent years, as computer-generated imagery has been applied to more industries, realistic facial animation is one of the important research topics. The current solution for realistic facial animation is to create realistic rendered 3D characters, but the 3D characters created by traditional methods are always different from the actual characters and require high cost in terms of staff and time. Deepfake technology can achieve the effect of realistic faces and replicate facial animation. The facial details and animations are automatically done by the computer after the AI model is trained, and the AI model can be reused, thus reducing the human and time costs of realistic face animation. In addition, this study summarizes the way human face information is captured and proposes a new workflow for video to image conversion and demonstrates that the new work scheme can obtain higher quality images and exchange effects by evaluating the quality of No Reference Image Quality Assessment.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권1호
• /
• pp.129-135
• /
• 2022

Real human digital models appear more and more frequently in VR/AR application scenarios, in which real-time markerless face capture animation of personalized virtual human faces is an important research topic. The traditional way to achieve personalized real human facial animation requires multiple mature animation staff, and in practice, the complex process and difficult technology may bring obstacles to inexperienced users. This paper proposes a new process to solve this kind of work, which has the advantages of low cost and less time than the traditional production method. For the personalized real human face model obtained by 3D reconstruction technology, first, use R3ds Wrap to topology the model, then use Avatary to make 52 Blend-Shape model files suitable for AR-Kit, and finally realize real-time markerless face capture 3D real human on the UE4 platform facial motion capture, this study makes rational use of the advantages of software and proposes a more efficient workflow for real-time markerless facial motion capture of personalized 3D real human models, The process ideas proposed in this paper can be helpful for other scholars who study this kind of work.

• 방송공학회논문지
• /
• 제15권3호
• /
• pp.391-406
• /
• 2010

디지털 마스터 배급 기반의 디지털시네마는 입체영화를 중심으로 발전하고 있다. 2004년에 발표된 Digital Cinema Initiatives (DCI)규격 1.0은 이미 입체영화 상영을 고려한 표준으로 발표되었다. 현재는 Society of Motion Picture and Television Engineers(SMPTE)에서 가정에서 상영되는 입체 콘텐츠 규격을 정의하기 위한 특별위원회가 구성되었다. 현재 헐리우드 중심의 상업용 입체 디지털시네마는 대부분 컴퓨터그래픽 기반의 애니메이션이 주류를 형성하고 있다. 그러나 영화적인 특성을 고려할 때 실사 영상을 획득, 편집후 상영하는 입체 디지털시네마 제작이 반드시 필요하다. 본 논문은 먼저 입체영상 제작흐름 중 NLE (non linear editing) 시스템에서 입체검안이 가능함을 증명한다. 그리고 입체 검안을 응용해 새로운 입체 디지털시네마 제작흐름을 제안하고자 한다. 실험결과 120Hz 기반의 3D Ready TV에서 콘텐츠 편집은 장애요소가 많았지만, Line Interleave방식의 모니터와 원평광 안경을 이용한 국산 입체모니터에서는 대부분 안정적인 편집이 가능하였다.

• 한국컴퓨터그래픽스학회논문지
• /
• 제20권3호
• /
• pp.9-17
• /
• 2014

본 논문에서는 대상이 되는 디지털 캐릭터가 기존 애니메이션 파이프라인에서 사용되는 수준의 복잡한 리깅을 가졌더라도, 해당 리깅의 리깅 공간(Rig-space)에 모션을 리타겟팅 할 수 있는 안정적이고 새로운 리타게팅 방법을 활용한다. 이를 위하여 다양하고 복잡한 방식으로 리깅된 서로 다른 캐릭터의 리깅 공간과 캐릭터 관절값 공간(Joint Parameter Space)간의 상관관계를 분석하고, 원본 모션을 최대한 보존하면서 효율적으로 리타게팅을 수행할 수 있는 비선형적 최적화 기법을 제안한다. 이로 인하여 애니메이터는 모션 캡쳐 등으로 얻어진 원본 모션을 수정할 때, 기존의 키프레이밍 작업과 동일한 리깅 파라미터를 사용할 수 있게 되어 직관적이면서도 빠르고 쉽게 모션을 수정할 수 있게 된다. 이 과정에서 애니메이터가 선호하는 작업 방식을 관찰한 후, 해당 과정을 최적화 과정에 반영함으로써 애니메이터가 수정하기에 매우 용이한 형태의 리타겟팅 결과물을 만들어 낼 수 있다.

• Journal of Information Technology Applications and Management
• /
• 제28권6호
• /
• pp.133-143
• /
• 2021

Unity's Cinemachine, one of the game production technologies, can produce 3D images. However, since Cinemachine is a game production tool, video creators may find it difficult because the work process of Cinemachine is unfamiliar and complicated. However, it is necessary to learn new technologies for the future of video contents that will be advanced in the future. In order to understand Chinemachine as a video producer, I would like to embody the scene of the movie. We are going to produce a storyboard scene for storytelling in Cinemachine. We defined the workflow of Unity Cinemachine while directing the scene by creating a story, and also checked the advantages and cautions. I hope it will be an opportunity to enjoy using Unity Cinemachine, which is constantly evolving.

• 융합신호처리학회논문지
• /
• 제25권2호
• /
• pp.113-118
• /
• 2024

최근 들어 인공지능, 컴퓨터 그래픽기술이 진화하면서 영화,광고, 방송, 게임, SNS 등 여러매체를 통해 다양한 가상휴먼이 등장하고 있다. 특히, 가상인플루언서를 중심으로 한 광고 마케팅 시장에서 가상휴먼은 시간과 비용 측면에서 기업의 중요한 홍보수단으로 이미 중요성이 입증된 상태이다. 국내는 가상 인플루언서 시장의 태동기 단계로 대기업 및 스타트업 경계없이 가상인플루언서 관련 신규 서비스를 출시 준비를 하고자 하나, 그 개발 프로세스가 공개되어 있지 않아 많은 비용을 지불해야 하는 상황이다. 이런 기업의 요구사항과 애로사항을 해결하기 위해 본 논문에서는 실사기반의 가상휴먼을 제작하기 위한 포토그래메트리기반 페이셜 캡춰 시스템을 구현하고, 이를 활용한 가상휴먼 모델링 및 활용사례에 대하여 고찰한다. 페이셜 캡처 후 실제 애니메이션이 가능한 과정까지의 복잡한 CG 작업 단계를 간소화할 수 있는 언리얼엔진기반의 메타휴먼 모델링을 통해 비용과 품질면에서 최적의 워크플로우에 대해서도 고찰하고, 또한 인스타그램 등 SNS마케팅에 활용한 사례에 대해서도 소개한다. 언리얼엔진기반의 워크플로우를 통해 기존의 CG작업과의 비교를 통해 제안한 워크플로우의 성능을 입증한다.