• Journal of the Korea Computer Graphics Society
• /
• v.18 no.1
• /
• pp.11-21
• /
• 2012

Point-based rendering has gained much attention as an alternative to polygon-based rendering because of its simplicity and flexibility. However, current point-based rendering techniques do not provide a sufficient rendering quality for translucent materials such as human skin. In this paper, we propose a point-based rendering framework with subsurface scattering of light, which is important to create the soft and semi-translucent appearance of human skin. To accurately simulate subsurface scattering in multi-layer materials, we present splat-based diffusion to apply a linear combination of several Gaussian basis functions to each splat in object space. Compared to existing point-based approaches, our method offers a significantly improved visual quality in rendering human faces.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.505-518
• /
• 2023

3D point cloud semantic segmentation is a computer vision task that involves dividing the point cloud into different objects and regions by predicting the class label of each point. Existing 3D semantic segmentation models have some limitations in performing sufficient fusion of multi-modal features while ensuring both characteristics of 2D visual features extracted from RGB images and 3D geometric features extracted from point cloud. Therefore, in this paper, we propose MMCA-Net, a novel 3D semantic segmentation model using 2D-3D multi-modal features. The proposed model effectively fuses two heterogeneous 2D visual features and 3D geometric features by using an intermediate fusion strategy and a multi-modal cross attention-based fusion operation. Also, the proposed model extracts context-rich 3D geometric features from input point cloud consisting of irregularly distributed points by adopting PTv2 as 3D geometric encoder. In this paper, we conducted both quantitative and qualitative experiments with the benchmark dataset, ScanNetv2 in order to analyze the performance of the proposed model. In terms of the metric mIoU, the proposed model showed a 9.2% performance improvement over the PTv2 model using only 3D geometric features, and a 12.12% performance improvement over the MVPNet model using 2D-3D multi-modal features. As a result, we proved the effectiveness and usefulness of the proposed model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.426-429
• /
• 2015

입체카메라에서 줌 사용시 컨버전스 포인트의 움직임에 따라 발생되는 시각적 불편의 문제와 거리감의 변동을 해결하기 위해 컨버전스 포인트 조정기법을 제시했었다. 본 연구에서는 이러한 조정기법의 우수성을 입증하기 위해 정량적 평가인 주시특성 분석을 설계했다. 입체영상에 대한 주관평가를 사용자의 시선움직임을 통해 정량적으로 파악하게 된다면 입체에 대한 사용자의 감성이미지를 보다 정확하게 파악할 수 있으며 이러한 자료를 통해 사용자 중심의 입체영상을 제작할 수 있는 환경을 제공하는 것이 가능할 것이다. 이를 통해 제시된 기법의 우수성을 정성과 정량적으로 입증한다.

• Journal of Internet Computing and Services
• /
• v.12 no.5
• /
• pp.87-100
• /
• 2011

In this paper, we address a video summarization task as generating both visually salient and semantically important video segments. In order to find salient data points, one can use the OC-SVM (One-class Support Vector Machine), which is well known for novelty detection problems. It is, however, hard to incorporate into the OC-SVM process the importance measure of data points, which is crucial for video summarization. In order to integrate the importance of each point in the OC-SVM process, we propose a fuzzy version of OC-SVM. The Importance-based Fuzzy OC-SVM weights data points according to the importance measure of the video segments and then estimates the support of a distribution of the weighted feature vectors. The estimated support vectors form the descriptive segments that best delineate the underlying video content in terms of the importance and salience of video segments. We demonstrate the performance of our algorithm on several synthesized data sets and different types of videos in order to show the efficacy of the proposed algorithm. Experimental results showed that our approach outperformed the well known traditional method.

• The Journal of the Korea Contents Association
• /
• v.21 no.7
• /
• pp.59-70
• /
• 2021

This paper studies and analyzes the effect of illustrations in picture books on time representation with fictional picture books as the study scope. In this paper, the time type of picture books can be divided into time point, timeline and time rhythm, referring to case analysis from time symbolic elements, picture layout and picture sequence respectively. First of all, time symbolic elements are referred to the time point and time rhythm. The materialized time symbolic element is things that can directly represent time and trigger associations with time; the color symbolic element means the color changes in the real world within a certain time; the contrast of light and shadow corresponds to the changes in a day. Fast-moving objects will be presented with dashed or blurred lines, while static, stable and slow objects will be depicted with solid lines. Secondly, the picture layout of illustrations in picture books is suitable for representing the content of the timeline and describing the sequence or causality of events. Finally, the picture sequence can represent the timeline, time rhythm and "synchronicity". It will make use of visual logic to win readers' trust in time information expressed in pictures, and then follow and connect viewpoints on the basis of adapting to reading habits. The essence of time representation in picture books is to express time by space, and use different combinations of elements in space and visual guidance to convey time information.

• Journal of Digital Convergence
• /
• v.15 no.5
• /
• pp.325-331
• /
• 2017

The purpose of this study is optional cinemagraph ads based on the case through the psychological theory of visual multimedia story qualitative analysis, quantitative analysis. Cinemagraph analysis would like to present the model. The analysis popular advertising model who starred with the higher profile in 2016 Gmaket of cinemagraph series of ads research, literature research, and Internet media. Analysis, case studies, etc. The analysis appeared around 10 percent was the most effective in the form of moving the form of copper wire. Part of the video cinema than the overall movement of the graph bigger visual flow effects is a dynamic. Moving the direction of the model used copper wires and broadly consistent with the product. Subject & Surrounding and margins are being used within one point or two points. The story of probability model in the short and expressing simple action of the product. Direction of the action, the proportion of multimedia for quantitative analysis of space story for the qualitative analysis of the periphery and jujebu, stories, such as the probability of four.For consideration the terms.

• Journal of the Economic Geographical Society of Korea
• /
• v.11 no.4
• /
• pp.564-579
• /
• 2008

It is often challenging to evaluate local spatial association among onedimensional vectors generally representing paired-location events where two points are physically or functionally connected. This is largely because of complex process of such geographic phenomena itself and partially representational complexity. This paper addresses an alternative way to identify spatially autocorrelated paired-location events (or vectors) at a local scale. In doing so, we propose a statistical algorithm combining univariate point pattern analysis for evaluating local clustering of origin-points and similarity measure of corresponding vectors. For practical use of the suggested method, we present an empirical application using transactions data in a local housing market, particularly recorded from 2004 to 2006 in Franklin County, Ohio in the United States. As a result, several locally characterized similar transactions are identified among a set of vectors showing various local moves associated with communities defined.

• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.289-296
• /
• 2019

In the era of M-ICT (mobile information communication technology), it is becoming more and more important to establish a city brand image that is "user-centered" and creates a new experience of "interaction between people, people and things, and people and space". The experience of city users on the brand image of a city is the key factor to determine the competitiveness of the city, among which the user's research on the touch point of the city brand is particularly important. The purpose of this study is to enhance the user's brand experience and enhance the city's brand competitiveness. The research methods of this paper are literature review and investigation. Firstly, the background and purpose of the study are expounded, then the characteristics and ways of user experience touch points are defined through the document review, and the multi-latitude composition model of city brand touch points is proposed. By means of user investigation, the structural characteristics of high frequency touch points between digital touch points and physical touch points are obtained. According to the problems found in the investigation, the optimal design strategy of touch point is put forward in combination with the case. The innovation of this study is to study the relationship between the city brand and the touch point of user experience from the perspective of user experience, and propose a multi-latitude model of the touch point of city brand.

• Journal of Broadcast Engineering
• /
• v.14 no.1
• /
• pp.36-43
• /
• 2009

Recently, the structural similarity (SSIM) index metric is proposed. In the present paper, a new framework, which is called visual SSIM (VSSIM), is proposed by incorporating crucial human factors into the SSIM. The human factors are foveation, luminance, frequency and motion information. The performance of VSSIM is evaluated by subjective quality test compliant with the Video Quality Expert Group (VQEG) multimedia group test plan. It shows that the visual SSIM is more correlated with the subjective quality result than the conventional SSIM.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.11
• /
• pp.147-155
• /
• 2015

For the image processing system to be classified the selected object in the nature, the rotation, scale and transition invariant features is to be necessary. There are many investigations to get the information for the object processing system and the log-polar transform which is to be get the invariant feature for the scale and rotation is used. In this paper, we suggested the 2 points polar coordinate transform methods to measure the selected object position out of the center in input image including the centroid method. In this proposed system, the position results of objects are very good, and we obtained the similarity ratio 99~104% for the object coordinate values.