• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.1-11
• /
• 2021

The purpose of our research is to efficiently deform a 3D models which is composed of a triangular mesh and a skeleton. We designed a novel inverse kinematics (IK) solver that calculates the updated positions of mesh vertices with fewer computing operations. Through our user interface, one or more markers are selected on the surface of the model and their target positions are set, then the system updates the positions of surface vertices to construct a deformed model. The IK solving process for updating vertex positions includes many computations for obtaining transformations of the markers, their affecting joints, and their parent joints. Many of these computations are often redundant. We precompute those redundant terms in advance so that the 3-nested loop computation structure was improved to a 2-nested loop structure, and thus the computation time for a deformation is greatly reduced. This novel IK solver can be adopted for efficient performance in various research fields, such as handling 3D models implemented by LBS method, or object tracking without any markers.

• Journal of the Korea Computer Graphics Society
• /
• v.15 no.2
• /
• pp.19-34
• /
• 2009

This paper presents an automatic rendering system for 3D meshes which generates images in the style of oriental black ink painting. In this paper, we analyze the characteristics of black ink painting and present some requirements for our black ink rendering system. Then we survey the steps used by artists to create black ink paintings. Based on the analysis of drawing steps, we propose a black ink rendering system which reproduces the key features of black ink painting through three sub-systems: the feature line layer, the interior shading layer, and the media layer. The main contribution of this paper is to introduce new methods which generate realistic and natural results very fast while any simulation methods are not used to satisfy real-time performance. We describe our implementation of each of these, and demonstrate our results in the major three styles of black ink painting: the outline style, the spontaneous style, and the outline-spontaneous style. Our system renders 3D models of moderate complexity at interactive frame rates. As a result, we expect that our system can be directly applied to real-time applications such as computer games and virtual environments.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.23-29
• /
• 2022

Virtual humans are implemented with dedicated modeling tools like Unity 3D Engine in virtual space (virtual reality, mixed reality, metaverse, etc.). Various human modeling tools have been introduced to implement virtual human-like appearance, voice, expression, and behavior similar to real people, and virtual humans implemented via these tools can communicate with users to some extent. However, most of the virtual humans so far have stayed unimodal using only text or speech. As AI technologies advance, the outdated machine-centered dialogue system is now changing to a human-centered, natural multi-modal system. By using several pre-trained networks, we implemented an emotion-based multi-modal dialogue system, which generates human-like utterances and displays appropriate facial expressions in real-time.

• Journal of the Korea Computer Graphics Society
• /
• v.21 no.1
• /
• pp.23-31
• /
• 2015

We present a method for creating realistic 2D stick figure animations easily and rapidly using captured motion data. Stick figure animations are typically created by drawing a single pose for each frame manually for the entire time interval. In contrast, our method allows the user to summarize an action (e.g. kick, jump) for an extended period of time into a single image in which one or more action lines are drawn over a stick figure to represent the moving directions of body parts. In order to synthesize a series of time-varying poses automatically from the given image, our system first builds a deformable character model that can make arbitrary deformations of the user's stick figure drawing in 2D plane. Then, the system searches for an optimal motion segment that best fits the given pose and action lines from pre-recorded motion database. Deforming the character model to imitate the retrieved motion segment produces the final stick figure animation. We demonstrate the usefulness of our method in creating interesting stick figure animations with little effort through experiments using a variety of stick figure styles and captured motion data.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.269-277
• /
• 2006

We propose a new expert system for recovering the broken fragments of relics into an original form using computer graphics and image processing. This paper presents a system with an application to tombstones objects of flat plane with letters carved in for assembling the fragments by placing their respective fragments in the right position. The matching process contains three sub-processes: aligning the front and letters of an object, identifying the matching directions, and determining the detailed matching positions. We apply least squares fitting, vector inner product, and geometric and RGB errors to the matching process. It turned out that 2-D translations via fragments-alignment enable us to save the computational load significantly. Based on experimental results from the damaged cultural fragments, the performance of the proposed method is illustrated.

• Journal of the Korea Computer Graphics Society
• /
• v.16 no.2
• /
• pp.29-37
• /
• 2010

In this paper, we present a novel deformation method for alleviating the asymmetry of a scanned 3D face considering facial features. To handle detailed areas of the face, we developed a new local 3D shape descriptor based on facial features and surface curvatures. Our shape descriptor can improve the accuracy when deforming a 3D face toward a symmetric configuration, because it provides accurate point pairing with respect to the plane of symmetry. In addition, we use point-based representation over all stages of symmetrization, which makes it much easier to support discrete processes. Finally, we performed a statistical analysis to assess subjects' preference for the symmetrized faces by our approach.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.2 s.46
• /
• pp.21-28
• /
• 2007

The facial modeling and animation technology had been studied in computer graphics field. The facial modeling technology is utilized much in virtual reality research purpose of MPEG-4 and so on and movie, advertisement, industry field of game and so on. Therefore, the development of 3D facial model that can do interaction with human is essential to little more realistic interface. We developed realistic and convenient 3D facial modeling system that using a optional facial image only. This system allows easily fitting to optional facial image by using the Korean standard facial model (generic model). So it generates intuitively 3D facial model as controling control points elastically after fitting control points on the generic model wire to the optional facial image. We can confirm and modify the 3D facial model by movement, magnify, reduce and turning. We experimented with 30 facial images of $630{\times}630$ sizes to verify usefulness of system that developed.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.4
• /
• pp.125-128
• /
• 2014

OpenGL ES(OpenGL for Embedded System) 2.0 is one of the most widely used 3D graphics API(application progrma interface) standard for smart phones and tablet PCs at this time. During programming with this API, they prefer desktop environment rather than the target mobile environment, which has relatively low computing power. Thus, we need to emulate the OpenGL ES 2.0 API on the desktop PCs, where only OpenGL API libraries are available. In this paper, we present technical difficulties and their solutions to emulate OpenGL ES 2.0 on desktop PCs. Our final implementation of OpenGL ES 2.0 emulation library works on desktop PCs and passed over more than 96% of the official CTS(conformance test suites) to prove the correctness of our implementation. Additionally, for the commercially available benchmark programs, our implementation shows equivalent execution speeds to the previous commercial OpenGL ES 2.0 implementations.

• Journal of Korea Game Society
• /
• v.6 no.4
• /
• pp.55-61
• /
• 2006

Graphics rendering pipeline (application, geometry, and rasterizer) is the core of real-time graphics which is the most important functionality for computer games. Usually this rendering process is completed by both the CPU and the GPU, and a bottleneck can be located either in the CPU or the GPU. This paper focuses on reducing the bottleneck between the CPU and the GPU. We are proposing a method for improving the performance of parallel processing for real-time graphics rendering by separating the CPU operations (usually performed using a thread) into two parts: pure CPU operations and operations related to the GPU, and let them operate in parallel. This allows for maximizing the parallelism in processing the communication between the CPU and the GPU. Some experiments lead us to confirm that our method proposed in this paper can allow for faster graphics rendering. In addition to our method of using a dedicated thread for GPU related operations, we are also proposing an algorithm for balancing the graphics pipeline using the idle time due to the bottleneck. We have implemented the two methods proposed in this paper in our networked 3D game engine and verified that our methods are effective in real systems.

• Journal of the Korea Computer Graphics Society
• /
• v.20 no.2
• /
• pp.1-11
• /
• 2014

The quality of 2D-to-3D conversion depends on the accuracy of the assigned depth to scene objects. Manual depth painting for given objects is labor intensive as each frame is painted. Specifically, a human is one of the most challenging objects for a high-quality conversion, as a human body is an articulated figure and has many degrees of freedom (DOF). In addition, various styles of clothes, accessories, and hair create a very complex silhouette around the 2D human object. We propose an efficient method to estimate visually pleasing depths of a human at every frame in a monocular video. First, a 3D template model is matched to a person in a monocular video with a small number of specified user correspondences. Our pose estimation with sequential joint angular constraints reproduces a various range of human motions (i.e., spine bending) by allowing the utilization of a fully skinned 3D model with a large number of joints and DOFs. The initial depth of the 2D object in the video is assigned from the matched results, and then propagated toward areas where the depth is missing to produce a complete depth map. For the effective handling of the complex silhouettes and appearances, we introduce a partial depth propagation method based on color segmentation to ensure the detail of the results. We compared the result and depth maps painted by experienced artists. The comparison shows that our method produces viable depth maps of humans in monocular videos efficiently.