• Journal of the Korea Computer Graphics Society
• /
• v.22 no.2
• /
• pp.11-19
• /
• 2016

This paper proposes a method to directly retarget facial motion capture data to the facial rig. Facial rig is an essential tool in the production pipeline, which allows helping the artist to create facial animation. The direct mapping method from the motion capture data to the facial rig provides great convenience because artists are already familiar with the use of a facial rig and the direct mapping produces the mapping results that are ready for the artist's follow-up editing process. However, mapping the motion data into a facial rig is not a trivial task because a facial rig typically has a variety of structures, and therefore it is hard to devise a generalized mapping method for various facial rigs. In this paper, we propose a data-driven approach to the robust mapping from motion capture data to an arbitary facial rig. The results show that our method is intuitive and leads to increased productivity in the creation of facial animation. We also show that our method can retarget the expression successfully to non-human characters which have a very different shape of face from that of human.

• Journal of the Korea Computer Graphics Society
• /
• v.20 no.3
• /
• pp.9-17
• /
• 2014

This paper presents a method to retarget a source motion to the rig-space parameter for a target character that can be equipped with a complex rig structure as used in traditional animation pipelines. Our solution allows the animators to edit the retargeted motion easily and intuitively as they can work with the same rig parameters that have been used for keyframe animation. To acheive this, we analyze the correspondence between the source motion space and the target rig-space, followed by performing non-linear optimization for the motion retargeting to target rig-space. We observed the general workflow practiced by animators and apply this process to the optimization step.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.442-445
• /
• 2011

본 논문에서는 3차원 head-tracked 디스플레이를 이용하여 스테레오 영상을 리타겟팅 하는 방법을 제안한다. 제안한 방법은 카메라 간격을 조절함으로써 사용자 시점에 맞는 스테레오 영상을 제공한다. 특히 중간 시점 영상 생성 시 발생하는 비폐색 영역에 대해 스테레오 일관성을 고려한 홀 필링(hole filling)을 적용하여 보다 편안하고, 개인별로 최적화 된 입체감 및 깊이감을 제공하도록 한다. 제안한 방법을 검증하기 위해 3차원 그래픽 모델을 이용해 결과 영상을 비교하였으며, 사용성 테스트를 통해 리타겟팅 된 스테레오 영상이 사용자가 입체영상을 인지하는데 미치는 효과를 확인하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.423-424
• /
• 2012

본 논문에서는 스테레오 영상의 중요 부분과 깊이 정보를 유지하며 영상의 크기를 변경하기 위한 새로운 warping 기반의 리타겟팅 기법을 제안한다. 단일 영상을 이용하는 기존의 알고리즘들은 스테레오 영상간의 일관성을 고려하지 않기 때문에 독립적으로 리타겟팅을 수행한 결과 영상의 3 차원 정보가 왜곡 된다. 반면 제안하는 알고리즘은 스테레오 영상에 격자를 생성하고 격자의 정점 매칭을 이용해 두 영상의 일관성을 유지한다. 또한 영상 내의 중요 물체가 유지되는 성능을 높이기 위해 sparse disparity map 을 생성한다. 다양한 스테레오 영상을 이용한 실험을 통해 제안하는 알고리즘이 다른 알고리즘에 비해 중요 물체와 3 차원 정보를 잘 보존하는 것을 확인한다.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.1-8
• /
• 2017

In this paper, we introduce a technique to retarget human motion data to the humanoid body in a constrained environment. We assume that the given motion data includes detailed interactions such as holding the object by hand or avoiding obstacles. In addition, we assume that the humanoid joint structure is different from the human joint structure, and the shape of the surrounding environment is different from that at the time of the original motion. Under such a condition, it is also difficult to preserve the context of the interaction shown in the original motion data, if the retargeting technique that considers only the change of the body shape. Our approach is to separate the problem into two smaller problems and solve them independently. One is to retarget motion data to a new skeleton, and the other is to preserve the context of interactions. We first retarget the given human motion data to the target humanoid body ignoring the interaction with the environment. Then, we precisely deform the shape of the environmental model to match with the humanoid motion so that the original interaction is reproduced. Finally, we set spatial constraints between the humanoid body and the environmental model, and restore the environmental model to the original shape. To demonstrate the usefulness of our method, we conducted an experiment by using the Boston Dynamic's Atlas robot. We expected that out method can help the humanoid motion tracking problem in the future.

• Korea Information Processing Society Review
• /
• v.19 no.1
• /
• pp.19-25
• /
• 2012

• The Magazine of the IEIE
• /
• v.39 no.10
• /
• pp.63-70
• /
• 2012

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06b
• /
• pp.236-239
• /
• 2008

본 논문에서는 영상의 중요한 정보를 유지하는 동시에 영상의 왜곡을 막으며, 영상의 크기를 줄이는 방법을 제시한다. 영상의 각 픽셀의 중요도를 측정 후, 가장 중요하지 않은 픽셀들을 제거하는데, 이 때 단순히 중요하지 않은 픽셀들을 제거하면, 이로 인해 영상의 왜곡이 생길 뿐 아니라 중요하지 않은 픽셀들이 가지고 있던 정황에 대한 정보도 잃게 된다. 이를 막기 위해 제시된 방법은 중요하지 않은 픽셀들을 제거한 후에, 그 픽셀들의 중요도를 주변으로 확산시키는 방법을 이용하여 영상의 왜곡을 막고, 영상의 정황을 보다 효과적으로 전달하며 영상 리타겟팅을 수행한다. 실험 결과는 제시된 방법의 효율성을 보여준다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.10
• /
• pp.791-795
• /
• 2009

There is a need for a system independent human data format that doesn't depend on a specific graphics tool or program to use interoperable human data in a network environment. To achieve this, the Web3D Consortium and ISO/IEC JTC1 WG6 developed the international draft standard ISO/IEC 19774 Humanoid Animation(H-Anim). H-Anim defines the data structure for an articulated human figure, but it does not yet define the data for human motion generation. This paper discusses a method of obtaining compatibility and independence of motion data between application programs, and describes a method of simplifying motion retargetting necessary for motion definition of H-Anim characters. In addition, it describes a method of generating H-Anim character animation using arbitrary 3D character models and arbitrary motion capture data without any inter-relations, and its implementation results.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.5
• /
• pp.63-71
• /
• 2011

In this paper, we propose a new real time image retargeting method which preserves the contents of an image. Since the conventional seam carving which is the well-known content-based image retargeting technology uses the dynamic programming method, the repetitive update procedure of the accumulation minimum energy map is absolutely needed. The energy map update procedure cannot avoid the processing time delay because of many operations by the image full-searching. The proposed method calculates the diffusion region of each seam candidates in the accumulation minimum energy map in order to reduce the update processing time. By using the diffusion region, several seams are extracted at the same time and the update number of accumulation energy map is reduced. Therefore, although the fast processing is possible, the quality of an image can be analogously maintained with an existing method. The experimental results show that the proposed method can preserve the contents of an image and adjust the image size on a real-time.