• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.465-472
• /
• 2022

In this paper, the style synthesis network is trained to generate style-synthesized video through the style synthesis through training Stylegan and the video synthesis network for video synthesis. In order to improve the point that the gaze or expression does not transfer stably, 3D face restoration technology is applied to control important features such as the pose, gaze, and expression of the head using 3D face information. In addition, by training the discriminators for the dynamics, mouth shape, image, and gaze of the Head2head network, it is possible to create a stable style synthesis video that maintains more probabilities and consistency. Using the FaceForensic dataset and the MetFace dataset, it was confirmed that the performance was increased by converting one video into another video while maintaining the consistent movement of the target face, and generating natural data through video synthesis using 3D face information from the source video's face.

• Journal of the Korea Computer Graphics Society
• /
• v.18 no.1
• /
• pp.1-9
• /
• 2012

Video-based modeling / rendering developed to produce photo-realistic video contents have been one of the important research topics in computer graphics and computer visions. To smoothly combine original input video clips and 3D graphic models, geometrical information of light sources and cameras used to capture a scene in the real world is essentially required. In this paper, we present a simple technique to estimate the position and orientation of an optimal light source from the topology of objects and the silhouettes of shadows appeared in the original video clips. The technique supports functions to generate well matched shadows as well as to render the inserted models by applying the estimated light sources. Shadows are known as an important visual cue that empirically indicates the relative location of objects in the 3D space. Thus our method can enhance realism in the final composed videos through the proposed shadow generation and rendering algorithms in real-time.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.71-72
• /
• 2019

본 논문에서는 계층구조 합성곱 신경망 기반의 고해상도 동영상 프레임 고속 보간 방법을 제안한다. 기존의 고해상도 동영상 프레임 보간 방법은 시간 해상도와 공간 해상도를 분리하여 보간 하기 때문에, 예측된 보간 프레임이 블러(blur) 열화를 갖는 문제를 보인다. 제안하는 방법에서는 이러한 문제를 해결하기 위하여 계층구조 합성곱 신경망 기반의 보간 방법을 이용한다. 제안하는 계층구조 합성곱 신경망은 우선 저해상도의 광학 흐름 추정지도를 생성하고 이를 고해상도로 복원하여 프레임 보간을 수행한다. 이때, 저해상도 광학 흐름 지도를 추정할 때 사용된 특징 정보들을 활용하여 고품질의 고해상도 광학 흐름 지도를 추정한다. 실험을 통하여 제안하는 방법이 고해상도 프레임을 고속으로 보간하며, 동시에 블러 열화에 대한 성능 향상을 가짐을 보였다.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.690-695
• /
• 2009

본 논문은 영화, 방송, 애니메이션 등의 다양한 동영상 콘텐츠에 수화 애니메이션을 합성하여 동영상 콘텐츠를 청각 및 언어장애인들에게 이해시키기 위한 수화 통역 VR 콘텐츠 시스템을 제안하고자 한다. 제안된 시스템은 수화 사전에 있는 수화들을 3D 애니메이션으로 DB화하기 위해, 모션 캡처 시스템과 데이터 글러브를 사용하여 실제 사람처럼 자연스러운 애니메이션을 생성하였다. 최종적으로 동영상 콘텐츠의 자막이나 대본의 구문분석을 한 후, 이를 수화용 단어자막을 통해 수화 애니메이션을 DB에서 검색한 후, 실시간적으로 기존 동영상 콘텐츠와 동기합성을 하여 수화 통역 콘텐츠를 제공하는 VR 콘텐츠 시스템을 구현하였고 이 시스템을 동화용 애니메이션에 적용하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.4
• /
• pp.617-623
• /
• 2018

In this paper, we propose a novel seamless video composition method based on shape matching and Poisson equation. Video composition method consists of video segmentation process and video blending process. In the video segmentation process, the user first sets a trimap for the first frame, and then performs a grab-cut algorithm. Next, considering that the performance of video segmentation may be reduced if the color, brightness and texture of the object and the background are similar, the object region segmented in the current frame is corrected through shape matching between the objects of the current frame and the previous frame. In the video blending process, the object of source video and the background of target video are blended seamlessly using Poisson equation, and the object is located according to the movement path set by the user. Simulation results show that the proposed method has better performance not only in the naturalness of the composite video but also in computational time.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.577-579
• /
• 2001

본 논문에서는 웨이블릿 변환 기법으로 키프레임을 분석하여 객체 영역을 추출함과 동시에 가상의 객체 영상을 현실감있게 합성하는 기술에 대하여 연구하였다. 가상의 객체 영상이나 실물체 영상을 비디오 영상내에 삽입하여 좀 더 현실감있는 새로운 동영상 비디오 데이터를 제작하는 데 초점을 맞추어 연구를 진행하였다. 웨이블릿 변환이 새로운 영상을 재구성하는데 커다란 기여를 하였으며 본 논문에서 제시한 AR 영상 합성 기법은 동영상 데이터를 합성하는데 사용자가 원하는 지점에 정확하게 영상의 특성정보를 충분히 잘 살린 새로운 방법의 시도였다. 또한, 영상의 캘리브 레이션 방법을 거치지 않고 비디오 영상의 회전행렬과 위치성분을 계산하여 매핑된 가상의 객체 영상을 영상 보간법을 적용하여 직접 가사의 객체 영상을 비디오 객체 영상을 비디오 영상열에 삽입한다. 제시한 영상 합성 기법은 가상의 객체 영상이 디지털 동영상내에 삽입되었을 때 가장 큰 문제점인 떨림 현상과 부조화 현상이 제거되었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.231-237
• /
• 2020

In this paper, we provide an efficient hybrid video blending scheme to improve the naturalness of composite video in Poisson equation-based composite methods. In image blending process, various blending methods are used depending on the purpose of image composition. The hybrid blending method proposed in this paper has the characteristics that there is no seam in the composite video and the color distortion of the object is reduced by properly utilizing the advantages of Poisson blending and alpha blending. First, after blending the source object by the Poisson blending method, the color difference between the blended object and the original object is compared. If the color difference is equal to or greater than the threshold value, the object of source video is alpha blended and is added together with the Poisson blended object. Simulation results show that the proposed method has not only better naturalness than Poisson blending and alpha blending, but also requires a relatively small amount of computation.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.2
• /
• pp.177-185
• /
• 2012

In this paper, we developed the composition system that it can efficiently edit camera recording data, images, office document such as powerpoint data, MS word data etc in real-time and broadcasting system that the file is made by the composition system. In this Study, we developed two kinds of algorithm; Approximate Composition for Optimization (ACFO) and Sequence Composition using Memory Que (SCUMQ). Especially, the system is inexpensive and useful because the system is based on mobile devices and PCs when lectures hope to make video institutional contents. Therefore, it can be contributed for e-learning and m-learning. In addition, the system can be applied to various fields, different kinds of multimedia creation, remote conferencing, and e-commerce.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.71-81
• /
• 2011

In order to easily create video tutorials, the algorithm is needed that video camera recording, white board images, video attachments, and document data are combined in real-time. In this study, we implemented the video lecture content creation system using wavelet-based lossless compression to composite multimedia objects in real-time and reproduce the images. Using commercially available PC can be useful when lecturers want to make video institutional contents, it can be operated easily and fastly. Therefore, it can be very efficient system for e-Learning and m-Learning. In addition, the proposed system including multimedia synthesis technology and real-time lossless compression technology can be applied to various fields, different kinds of multimedia creation, remote conferencing, and e-commerce so there are highly significant.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.9
• /
• pp.105-113
• /
• 2009

This paper is aimed at embodying the optimal system for foreign workforce supply of nation in order to introduce qualified foreign workers at the age of eleven thousand foreigners. It is difficult to employ foreign workers qualified and it makes job rosters' confidence fall down which is the supplementary resources when selecting due to the insufficient job seekers' detailed information. Therefore, the moving control system should be added in current system to deal with these problems. For this, in this paper, we propose that the moving picture embedded system applies to the current EPS utilizing multimedia, network and database technologies as regards adding the function of the moving picture synthesis to recent system. It also suggests the advanced foreign employment control system related to the advanced system which makes employers to hire foreign workers satisfying their requirements and demand.