• Journal of the Korea Computer Graphics Society
• /
• v.30 no.2
• /
• pp.21-29
• /
• 2024

Although there is an increasing demand for capturing various natural motions, collecting climbing motion data is difficult due to technical complexities, related to obscured markers. Additionally, scanning climbing structures and preparing diverse routes further complicate the collection of necessary data. To tackle this challenge, this paper proposes a climbing motion synthesis using reinforcement learning. The method comprises two learning stages. Firstly, the hanging policy is trained to grasp holds in a natural posture. Once the policy is obtained, it is used to extract the positions of the holds, postures, and gripping states, thus forming a dataset of favorable initial poses. Subsequently, the climbing policy is trained to execute actual climbing maneuvers using this initial state dataset. The climbing policy allows the character to move to the target location using limbs more evenly in a natural posture. Experiments have shown that the proposed method can effectively explore the space of good postures for climbing and use limbs more evenly. Experimental results demonstrate the effectiveness of the proposed method in exploring optimal climbing postures and promoting balanced limb utilization.

• Journal of Korea Multimedia Society
• /
• v.14 no.8
• /
• pp.1082-1093
• /
• 2011

Traditional rendering of cartoon character cannot revive the feeling of concept drawings properly. In this paper, we propose capture technology to get toon shading model from the concept drawings and with this technique, we provide a new novel system to render 3D cartoon character. Benefits of this system is to cartoonize the 3D character according to saliency to emphasize the form of 3D character and further support the sketch-based user interface for artists to edit shading by post-production. For this, we generate texture automatically by RGB color sorting algorithm to analyze color distribution and rates of selected region. In the cartoon rendering process, we use saliency as a measure to determine visual importance of each area of 3d mesh and we provide a novel cartoon rendering algorithm based on the saliency of 3D mesh. For the fine adjustments of shading style, we propose a user interface that allow the artists to freely add and delete shading to a 3D model. Finally, this paper shows the usefulness of the proposed system through user evaluation.

• Journal of Korea Society of Industrial Information Systems
• /
• v.8 no.4
• /
• pp.55-63
• /
• 2003

The game & multimedia industry is a high-valued industry comparing to any industry. Also, it has been shown the possibility as considerably bright future industry due to a development of the Internet, an explosive growth of on-line game market, and a union with virtual reality technology Since an on-line game having a clear profit model is expanding to PC and other platform, it brings to us a large change throughout the whole game industry. In order to develop a game, we need a number of elements. A game character among them delivers to a user the overall characteristics of a game as a visual representation and makes us access to a game directly and sensuously. A game character of on-line game is considerable in an operation in the volume of initial sales from a viewpoint of marketing. In addition, it affects to secure users and be immersed in a game. In this paper, we propose a production skill of an efficient 3D game character for 3D on-line game.

• Cartoon and Animation Studies
• /
• s.37
• /
• pp.439-461
• /
• 2014

Art has evolved into remarkable changes in its art form maintaining a close link with the contemporary scientific technologies that gave birth to new tools of expression in each era. Animation is an art form in an inextricable connection with technological aspects because it was spawned by the technical background like movies. In this regard, animation is often viewed very strongly by technical advancements in terms of an aesthetic approach. John Whitney Sr., one of the pioneers in computer graphics arts, turned his attention to the new technology called computer graphics as a means to visualize images and movement. The advent of a new medium had a strong influence not only on tools and means for novel expression but also on the gradual shift in thinking about arts and even the audiences' taste. In the 1980s, animation was combined with computer technology and the rapid progress of computer graphic technology opened up the era of new visual aesthetics, Today, the development of digital technology presents a different dimension of realism, either advocating hyperrealism by digital actors or presenting new illusionism by classic cartoon characters emphasized in a distortion or metamorphosis from a real life in order to consolidate animation realism. Based on the two perspectives mentioned above, this study can identify methods of digital character appropriation focused on the works of the ACM SIGGRAPH Asia and find how the relationship between art and technology has changed the digital realism and evolved the digital character as the digital technology has developed.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.10
• /
• pp.1291-1300
• /
• 2001

This article come to study the visualization representation technique of eye brain of person, basing on the ground of the dynamic graphics which is able to change the real time, manipulating the image as graphic factors of the multi-data. And the important thought in such realization is as follows ; corresponding the character points of human face and the parameter control value which obtains basing on the existing image recognition algorithm to the multi-dimensional data, synthesizing the image, it is to create the virtual image from the emotional expression according to the changing contraction expression. The proposed DyFIG system is realized that it as the completing module and we suggest the module of human face graphics which is able to express the emotional expression by manipulating and experimenting, resulting in realizing the emotional data expression description and technology.

• Journal of Korea Multimedia Society
• /
• v.16 no.11
• /
• pp.1348-1356
• /
• 2013

Disney Animation has showed not only artistic excellence but also technological innovations through a lot of animation films that they released. Especially with the unique concept that free-willed game characters dive into different worlds of games in animation film, received both critical and commercial acclaim for its stunning visuals and outstanding CG (computer graphics) effects. The purpose of this study is to analyze different styles of game worlds, Disney's layout pipeline, and in-house camera capture system used in . This paper analyzes that three game worlds in this film such as Fix-It Felix Jr., Sugar Rush, and Hero's Duty express different styles by using appropriate character animation and camera movements. Especially Hero's Duty game which new in-house camera capture system is extensively used maximizes unseen visuals by perfectly making realistic and believable game world. Disney's newly developed in-house camera capture system, which is used in this film for the first time, allows real camera's motion and shake and real-time camera's movement and correction within animation set. Result of this study proves that this system improves directing of feature animation and enhance efficiency of the layout department's production process. Therefore, it contributes to a great extent to development of animation films' business.

• Journal of the Korea Computer Graphics Society
• /
• v.13 no.3
• /
• pp.11-18
• /
• 2007

Creating stylistic facial animation is one of the most important problems in character animation. Traditionally facial animation is created manually by animators of captured using motion capture systems. But this process is very difficult and labor-intensive. In this work, we present an intuitive, easy-to-use, sketch-based user interface system that facilitates the process of creating facial animation and key-frame interpolation method using facial capture data. The user of our system is allowed to create expressive speech facial animation easily and rapidly.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.2
• /
• pp.41-47
• /
• 2017

In this paper, we present a method for data-driven correction of the noisy motion data captured from a low-end RGB-D camera such as the Kinect device. For this purpose, our key idea is to construct a synchronized motion database captured with Kinect and additional specialized motion capture device simultaneously, so that the database contains a set of erroneous poses from Kinect and their corresponding correct poses from the mocap device together. In runtime, given motion captured data from Kinect, we search the similar K candidate Kinect poses from the database, and synthesize a new motion only by using their corresponding poses from the mocap device. We present how to build such motion database effectively, and provide a method for querying and searching a desired motion from the database. We also adapt the laze learning framework to synthesize the corrected poses from the querying results.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.1
• /
• pp.23-29
• /
• 2023

In this paper, we introduce a method to obtain high-quality results at a low cost for simulating musculoskeletal characters based on data from the reference motion through motion capture on two-legged walking through reinforcement learning. We reset the motion data of the reference motion to allow the character model to perform, and then train the corresponding motion to be learned through reinforcement learning. We combine motion imitation of the reference model with minimal metabolic energy for the muscles to learn to allow the musculoskeletal model to perform two-legged walking in the desired direction. In this way, the musculoskeletal model can learn at a lower cost than conventional manually designed controllers and perform high-quality bipedal walking.

• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.591-600
• /
• 2006

This paper describes the development and implementation of a algorithm to decompose word images from image regions mixed text/graphics in document images using statistical analyses. To decompose word images from image regions, the character components need to be separated from graphic components. For this process, we propose a method to separate them with an analysis of box-plot using a statistics of structural components. An accuracy of this method is not sensitive to the changes of images because the criterion of separation is defined by the statistics of components. And then the character regions are determined by analyzing a local crowdedness of the separated character components. finally, we devide the character regions into text lines and word images using projection profile analysis, gap clustering, special symbol detection, etc. The proposed system could reduce the influence resulted from the changes of images because it uses the criterion based on the statistics of image regions. Also, we made an experiment with the proposed method in document image processing system for keyword spotting and showed the necessity of studying for the proposed method.