• International Journal of Internet, Broadcasting and Communication
• /
• 제16권2호
• /
• pp.81-86
• /
• 2024

Advancements in generative AI are reshaping graphic and 3D content design landscapes, where AI not only enriches graphic design but extends its reach to 3D content creation. Though 3D texture mapping through AI is advancing, AI-generated 3D modeling technology in this realm remains nascent. This paper presents AI 2D image-driven 3D modeling techniques, assessing their viability in 3D content design by scrutinizing various algorithms. Initially, four OBJ model-exporting AI algorithms are screened, and two are further evaluated. Results indicate that while AI-generated 3D models may not be directly usable, they effectively capture reference object structures, offering substantial time savings and enhanced design efficiency through manual refinements. This endeavor pioneers new avenues for 3D content creators, anticipating a dynamic fusion of AI and 3D design.

• 한국멀티미디어학회논문지
• /
• 제11권6호
• /
• pp.746-754
• /
• 2008

A 3D stereoscopic image is generated by interdigitating every scene with video editing tools that are rendered by two cameras' views in 3D modeling tools, like Autodesk MAX(R) and Autodesk MAYA(R). However, the depth of object from a static scene and the continuous stereo effect in the view of transformation, are not represented in a natural method. This is because after choosing the settings of arbitrary angle of convergence and the distance between the modeling and those two cameras, the user needs to render the view from both cameras. So, the user needs a process of controlling the camera's interval and rendering repetitively, which takes too much time. Therefore, in this paper, we will propose the 3D stereoscopic image editing system for solving such problems as well as exposing the system's inherent limitations. We can generate the view of two cameras and can confirm the stereo effect in real-time on 3D modeling tools. Then, we can intuitively determine immersion of 3D stereoscopic image in real-time, by using the 3D stereoscopic image preview function.

• 한국정보과학회논문지:데이타베이스
• /
• 제30권2호
• /
• pp.145-156
• /
• 2003

현존하는 대부분의 내용 기반 이미지 검색 시스템은 칼라, 모양, 텍스처 특징을 이용한 유사도-기반 검색에 초점을 맞추고 있다. 신경과학 이미지 데이타베이스의 경우, 이미지에 대한 전역적 평균 특징 값을 기반으로 한 유사 이미지의 검색이 임상 병리학자들에게는 전혀 도움이 되지 않는 다는 것을 발견하였다. 신경과학 데이터베이스 상의 이미지에 대한 실용적인 내용 기반 검색을 실현하기 위해서는 이미지의 내부 내용이나 의미를 표현하는 일이 필요하다. 본 논문에서는 이러한 이미지들에 대해 보다 유용한 검색을 지원하기 위하여 이미지 내용과 그에 관련된 개념 지식을 표현하는 방법을 제시한다. 또한 객체지향 메시지 경로 식을 이용하여 이러한 고급 검색을 지원하기 위한 연산의 의미를 기술한다. 제안된 기법은 유연하고 확장 가능하므로 보다 강화된 내용 검색을 위해 이미지 내용에 대한 보다 많은 의미를 점진적으로 추가해 나갈 수 있다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1383-1385
• /
• 2003

Remote sensing has been widely used in the exploration of groundwater. In this paper, on the establishment of empirical function between ground water and soil moisture content 6S code is used to reduce uncertainties in the remote sensing of groundwater. Then ground water levels are calculated using 6S corrected and uncorrected ETM+ image along with isochronous meteorological information. Greater correspondence between field examined and satellite monitoring data is obtained from corrected image than from the uncorrected image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권7호
• /
• pp.3284-3306
• /
• 2018

This study proposes a method to develop an authoring system(GeoMaTree) for diverse trees that constitute a virtual landscape. The GeoMaTree system enables the simple, intuitive production of an efficient structure, and supports real-time processing. The core of the proposed system is a procedural modeling based on a mathematical model and an application that supports digital content creation on diverse platforms. The procedural modeling allows users to control the complex pattern of branch propagation through an intuitive process. The application is a multi-resolution 3D model that supports appropriate optimization for a tree structure. The application and a compatible function, with commercial tools for supporting the creation of realistic synthetic images and virtual landscapes, are implemented, and the proposed system is applied to a variety of 3D image content.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권2호
• /
• pp.126-136
• /
• 2004

이 논문은 색상과 위치정보를 이용한 새로운 내용기반 영상검색 알고리즘을 제안한다. 이를 위해서. 질의가 주어졌을 경우, 데이타베이스의 검색공간을 줄일 목적으로 두 가지 종류의 색인 키(Key)를 제시하는데 하나는 영상의 고유한 색상 구성적 특성을 나타내는 주요 색상세트(MCS, Main Colors' Set)이고 다른 하나는 주요 색상마다의 분포 및 위치적 특성을 나타내는 분포 블록기호(DBS, Distribution Block Signature)이다. 이 두 가지 필터(Filter)를 연속적으로 적용하면 영상 데이터베이스로부터 잠재성이 높은 유사 후보 영상만을 걸러내게 된다. 이어서 보다 높은 검색성능을 얻기 위해 새롭게 제안한 쿼드모델 (Quad Modeling)과 유사도 피드백 메커니즘을 이용한다. 이 방법은 색상과 위치정보에 대한 가중치를 역동적으로 조절함으로써 검색성능을 향상시킨다. 실험을 통해서 제안된 알고리즘이 성공적으로 영상검색에 사용될 수 있음을 보인다.

• ETRI Journal
• /
• 제36권3호
• /
• pp.450-459
• /
• 2014

In this paper, we present a new, easy-to-generate system that is capable of creating virtual 3D tree models and simulating a variety of growth processes of a tree from a single, real tree image. We not only construct various tree models with the same trunk through our proposed digital image matting method and skeleton-based abstraction of branches, but we also animate the visual growth of the constructed 3D tree model through usage of the branch age information combined with a scaling factor. To control the simulation of a tree growth process, we consider tree-growing attributes, such as branching orders, branch width, tree size, and branch self-bending effect, at the same time. Other invisible branches and leaves are automatically attached to the tree by employing parametric branch libraries under the conventional procedural assumption of structure having a local self-similarity. Simulations with a real image confirm that our system makes it possible to achieve realistic tree models and growth processes with ease.

• Asia pacific journal of information systems
• /
• 제29권2호
• /
• pp.181-202
• /
• 2019

The purpose of this study is to explore the effect of different types of simultaneous presentation (i.e., reviewer information, textual and visual content, and similarity between textual-visual contents) on review usefulness and review enjoyment in online restaurant reviews (ORRs), as they are interrelated yet have rarely been examined together in previous research. By using Latent Dirichlet Allocation (LDA) topic modeling and state-of-the-art machine learning (ML) methodologies, we found that review readability in textual content and salient objects in images in visual content have a significant impact on both review usefulness and review enjoyment. Moreover, similarity between textual-visual contents was found to be a major factor in determining review usefulness but not review enjoyment. As for reviewer information, reputation, expertise, and location of residence, these were found to be significantly related to review enjoyment. This study contributes to the body of knowledge on ORRs and provides valuable implications for general users and managers in the hospitality and tourism industries.

• 보존과학회지
• /
• 제38권1호
• /
• pp.55-63
• /
• 2022

The Bigyeokjincheolloe (bomb shell), a scientific cultural heritage, has outstanding historical value for sustaining a gunpowder weapon of Joseon. In this study, the bomb shell was modeled through three-dimensional (3D) scanning centered on the external shape and 𝛾-ray radiography-based on the internal shape. In particular, to improve the contrast in the radiographic image, optimization and image processing were performed. After these processes, the thickness of the inner wall (2.5 cm on average) and the positions of the three mold chaplets were clearly revealed. For exhibition purposes, the 3D model of the bomb shell was output to a 3D printer and the output was rendered realistic by coloring. In addition, the internal functional elements, such as Mokgok, fuse, mud, gunpowder, and caltrops, were reproduced through handwork. The results will contribute to the study of digital heritages in two ways. First, the internal and external shapes of the bomb shell were modeled by fusing two different technologies, namely, 3D scanning and 𝛾-ray radiography. Second, the internal shape of the bomb shell was constructed from the original form data and the reproduction was utilized for museum exhibitions. The developed modeling approach will greatly expand the scope of museum exhibitions, from those centered on historical content to those centered on scientific content.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅲ
• /
• pp.1515-1518
• /
• 2003

This paper suggests the condensed two-stage retrieval method for fast image retrieval in the content-based image retrieval system, and proves the validity of the performance. The condensed two-stage retrieval method reduces the overall response time remarkably while it maintains relevance with the conventional exhaustive search method. It is explained by properties of the Cauchy-Schwartz inequality. In experimental result, it turns out that there is an optimal value of condensation ratio which minimizes the overall response time. We analyze the optimal condensation ratio by modeling a similarity computation time mathematically.