• 한국의류학회지
• /
• 제36권6호
• /
• pp.631-640
• /
• 2012

This research project investigates the differences of various body locations (between 3D body models) and drapes garments digitally onto 3D body models. Three different subject models will be given explication. It consisted of (1) data collection of three-dimensional scans (2) creation of 3D body representations (3) comparison of avatar shapes and measurements (4) visualization and assessment of 3D body models and their 3D virtual garments. The study tests a theory of impact by differences in avatars by pattern design. A visual inspection of avatars showed clear differences between the six avatar types (in the generating process); however, there was notably less difference between 3D garment simulations based upon the six avatars produced. This demonstrated that there was less influence on the 3D garments than was predicted after a visual inspection of the avatars.

• 한국산업정보학회논문지
• /
• 제25권5호
• /
• pp.1-11
• /
• 2020

가상착용기술은 온라인 의류 쇼핑 활성화를 위해 중요한 기술이다. 최근 이미지 기반 가상착용기술은 의상과 착용 대상 신체의 3차원 정보가 필요하지 않다는 실용성 때문에 큰 관심을 받고 있다. 그러나 기존의 이미지 기반 알고리즘의 2차원 기하변형 방식의 한계로 인하여 대상 인물의 포즈와 의상 이미지의 형태가 큰 차이가 있는 경우 자연스러운 의상변형을 하지 못한다. 본 논문에서는 이러한 문제를 해결하기 위해 3차원 인체 모델을 이용하여 2차원 의상 사진으로 부터 의상의 3차원 모델을 생성하고, 대상 인물의 자세와 체형에 맞게 3차원 변형 후 렌더링하고 대상 인간 이미지와 혼합을 통하여 가상착용 이미지를 생성할 수 있다. 기존 연구에서 사용된 VITON 데이터 세트를 사용한 실험 결과는 3차원 변형이 요구되는 경우에 2차원 이미지 기반 가상착용 결과들에 비교했을 때 자연스러운 결과를 보인다.

• Journal of Information Processing Systems
• /
• 제16권2호
• /
• pp.343-359
• /
• 2020

In this paper, a new algorithm is proposed for three-dimensional (3D) shape recognition using local features of model views and its sparse representation. The algorithm starts with the normalization of 3D models and the extraction of 2D views from uniformly distributed viewpoints. Consequently, the 2D views are stacked over each other to from view cubes. The algorithm employs the descriptors of 3D local features in the view cubes after applying Gabor filters in various directions as the initial features for 3D shape recognition. In the training stage, we store some 3D local features to build the prototype dictionary of local features. To extract an intermediate feature vector, we measure the similarity between the local descriptors of a shape model and the local features of the prototype dictionary. We represent the intermediate feature vectors of 3D models in the sparse domain to obtain the final descriptors of the models. Finally, support vector machine classifiers are used to recognize the 3D models. Experimental results using the Princeton Shape Benchmark database showed the average recognition rate of 89.7% using 20 views. We compared the proposed approach with state-of-the-art approaches and the results showed the effectiveness of the proposed algorithm.

• Biomaterials and Biomechanics in Bioengineering
• /
• 제3권3호
• /
• pp.141-155
• /
• 2016

Two-dimensional (2D) cell culture and in vivo cancer model systems have been used to understand cancer biology and develop drug delivery systems for cancer therapy. Although cell culture and in vivo model studies have provided critical contribution about disease mechanism, these models present important problems. 2D tissue culture models lack of three dimensional (3D) structure, while animal models are expensive, time consuming, and inadequate to reflect human tumor biology. Up to the present, scaffolds and 3D matrices have been used for many different clinical applications in regenerative medicine such as heart valves, corneal implants and artificial cartilage. While tissue engineering has focused on clinical applications in regenerative medicine, scaffolds can be used in in vitro tumor models to better understand tumor relapse and metastasis. Because 3D in vitro models can partially mimic the tumor microenvironment as follows. This review focuses on different scaffold production techniques and polymer types for tumor model applications in cancer tissue engineering and reports recent studies about in vitro 3D polymeric tumor models including breast, ewing sarcoma, pancreas, oral, prostate and brain cancers.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2006년도 춘계학술발표회 논문집
• /
• pp.387-392
• /
• 2006

3D-based information is needed increasingly as well as 2D Information as cities grow and buildings become large and complex, and use of 3D-models is getting attention to handle such problems. However, there are limitations in using 3D-models because most applications and research efforts using them have been for visual analysis. This study presents a method to find optimal paths in indoor spaces as an illustration for using 3D-models in spatial analysis. We modeled rooms, paths and other facilities in a building as individual 3D objects. We made it possible to find paths based on network structure by integrating the vector-based networks of 2D-GIS and 3D-model.

• 한국CDE학회논문집
• /
• 제6권2호
• /
• pp.133-139
• /
• 2001

Since a great number of 2D engineering drawings are being used in industry and at the same time 3D CAD becomes popular in recent years, we need to reconstruct 3D CAD models from 2D legacy drawings. In this thesis, a combination of a feature recognition method and an expert system is suggested for the 3D solid model reconstruction. Modeling primitives of 3D CAD systems are recognized and constructed by using the pattern matching technique of the features modeling. Additional information for the 3D model reconstruction can be generated by extracting symbols or text entities which are related to form entities. For complex and indefinite cases which cannot be solved by the process of feature recognition, an expert system with a rule base has been used for decision-making. A 3D reconstruction system which recognizes 2D DXF drawing files has been implemented where models composed with protrusions, holes, and cutouts can be handled.

• 복식문화연구
• /
• 제25권3호
• /
• pp.270-284
• /
• 2017

This study aimed to create 3D-printed insoles for flat-footed senior men using 3D systems. 3D systems are product-manufacturing systems that use 3-dimensional technologies like 3D scanning, 3D modeling, and 3D printing. This study used a 3D scanner (NexScan2), 3D CAD programs including Rapidform, AutoCAD, SolidWorks, Nauta+ compiling program, and a 3D printer. In order to create insoles for flat-footed senior men, we analyzed horizontal sections of 3D foot scans We selected 20 flat-footed and 20 normal-footed subjects. To make the 3D insole models, we sliced nine lines on the surface of the subjects' 3D foot scans, and plotted 144 points on the lines. We calculated the average of these 3D coordinates, then located this average within the 3D space of the AutoCAD program and created 3D sole models using the loft surface tools of the SolidWorks program. The sole models for flat feet differed from those of normal feet in the depth of the arch at the inner sideline and the big toe line. We placed the normal-footed sole model on a flat-footed sole model, and the combination of the two models resulted in the 3D insole for flat feet. We printed the 3D modeled insole using a 3D printer. The 3D printing material was an acrylic resin similar to rubber. This made the insole model flexible and wearable. This study utilized 3D systems to create 3D insoles for flat-footed seniors and this process can be applied to manufacture other items in the fashion industry as well.

• International Journal of Advanced Culture Technology
• /
• 제11권4호
• /
• pp.346-351
• /
• 2023

With the rapid development of Artificial Intelligence (AI) technology, there is an increasing variety of methods for creating 3D models. These include innovations such as text-only generation, 2D images to 3D models, and combining images with cue words. Each of these methods has unique advantages, opening up new possibilities in the field of 3D modeling. The purpose of this study is to explore and summarize these methods in-depth, providing researchers and practitioners with a comprehensive perspective to understand the potential value of these methods in practical applications. Through a comprehensive analysis of pure text generation, 2D images to 3D models, and images with cue words, we will reveal the advantages and disadvantages of the various methods, as well as their applicability in different scenarios. Ultimately, this study aims to provide a useful reference for the future direction of AI modeling and to promote the innovation and progress of 3D model generation technology.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2006년도 춘계학술발표회 논문집
• /
• pp.333-337
• /
• 2006

As IT-based technologies develop, 3D GIS applications that digitally model real environment are being increased. Although the terms related with 3D CIS are used increasingly, research efforts and applications are mostly limited to only 2D GIS or 3D modeling respectively. The reasons are viewed that there have been less research findings or software tools about integration of 2D GIS and 3B models. Thus, this study presents a method to integrate 2D GIS and 3D models by using database as the means for linkage. To illustrate the process, we developed a prototype application using C# language. Within an interface we showed how to integrate different libraries - EON Studio and MapObjects. We expect that the integration techniques we suggest here can be applied to such areas as disaster prevention, transportation and natural resources management.

• 전자통신동향분석
• /
• 제34권4호
• /
• pp.15-22
• /
• 2019

Recent technological advances in three-dimensional (3D) sensing devices and machine learning such as deep leaning has enabled data-driven 3D applications. Research on artificial intelligence has developed for the past few years and 3D deep learning has been introduced. This is the result of the availability of high-quality big data, increases in computing power, and development of new algorithms; before the introduction of 3D deep leaning, the main targets for deep learning were one-dimensional (1D) audio files and two-dimensional (2D) images. The research field of deep leaning has extended from discriminative models such as classification/segmentation/reconstruction models to generative models such as those including style transfer and generation of non-existing data. Unlike 2D learning, it is not easy to acquire 3D learning data. Although low-cost 3D data acquisition sensors have become increasingly popular owing to advances in 3D vision technology, the generation/acquisition of 3D data is still very difficult. Even if 3D data can be acquired, post-processing remains a significant problem. Moreover, it is not easy to directly apply existing network models such as convolution networks owing to the various ways in which 3D data is represented. In this paper, we summarize technological trends in AI-based 3D content generation.