• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.10C
• /
• pp.1007-1016
• /
• 2005

This paper presents a feature extraction method for shape based retrieval of 3D models. Since the feature descriptor of 3D model should be invariant to translation, rotation and scaling, it is necessary to preprocess the 3D models to represent them in a canonical coordinate system. We use the PCA(Principal Component Analysis) method to preprocess the 3D models. Also, we apply that to make a MBR(Minimum Boundary Rectangle) and a circumsphere. The proposed algorithm is as follows. We generate a circumsphere around 3D models, where radius equals 1(r=1) and locate each model in the center of the circumsphere. We produce the concentric spheres with a different radius($r_i=i/n,\;i=1,2,{\ldots},n$). After looking for meshes intersected with the concentric spheres, we compute the curvature of the meshes. We use these curvatures as the model descriptor. Experimental results numerically show the performance improvement of proposed algorithm from min. 0.1 to max. 0.6 in comparison with conventional methods by ANMRR, although our method uses .relatively small bins. This paper uses $R{^*}-tree$ as the indexing.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.715-718
• /
• 2022

단일 이미지로부터 3D 모델을 생성하는 방법은 메타버스와 가상현실 콘텐츠에 대한 필요성이 높아짐에 따라, 보다 효율적인 모델 생성방법으로서 관심이 높아지고 있다. 본 논문에서는 단일 이미지로부터 3D 모델을 자동 생성하는 기존 딥-뉴럴 네트워크들을 대상으로, 생성되는 3D 모델의 유형에 따라 기존 네트워크들을 분류하고, 주요 딥-뉴럴 네트워크의 형태와 특징, 그리고 모델 생성의 성능을 분석하고자 한다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.3
• /
• pp.27-33
• /
• 2003

The image-based 3D modeling is the technique of generating a 3D graphic model from images acquired using cameras. It is being researched as an alternative technique for the expensive 3D scanner. In this paper, we propose the image-based, 3D modeling system using calibrated stereo cameras. The proposed algorithm for rendering, 3D model consists of three steps, camera calibration, 3D reconstruction, and 3D registration step. In the camera calibration step, we estimate the camera matrix for the image aquisition camera. In the 3D reconstruction step, we calculate 3D coordinates using triangulation from corresponding points of the stereo image. In the 3D registration step, we estimate the transformation matrix that transforms individually reconstructed 3D coordinates to the reference coordinate to render the single 3D model. As shown the result, we generated relatively accurate 3D model.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.37 no.6
• /
• pp.1109-1117
• /
• 2017

Recently, 3D printer technology has been attracting attention in various industrial fields, and research papers are being conducted to utilize 3D printers in the construction industry. Actual structures such as bridges and buildings are being printed to 3D printers, and various applications such as mock-up structures using 3D printers are being proposed. In order to utilize 3D printer technology in the construction field, a 3D model is required, and the 3D BIM data produced at the design stage can be printed by a 3D printers, saving the cost and time of 3D model generation. However, 3D BIM data often does not satisfy the conditions for 3D printer output, causing many errors on output. In this paper, authors propose a problem analysis for 3D BIM model output to 3D printer and a method for reducing errors in 3D printing process of 3D BIM model. In addition, this paper presents a practical application of 3D model output from 3D printer.

• Journal of Korea Multimedia Society
• /
• v.10 no.4
• /
• pp.527-536
• /
• 2007

This paper proposes a 3D fashion design system that generates a 3D clothes model by using 2D patterns of clothes and drapes the 3D clothes model on a 3D human model. In the proposed system, 2D patterns of clothes are designed by selecting comer points of 2D mesh. After designing 2D patterns, a 3D clothes model is designed by describing the control points to be connected between 2D patterns. The proposed system reads a 3D human body model file and the designed 3D clothes model and creates a 3D human model putting on the clothes by using the mass-spring model based physical simulation. It calculates collision and reaction between the triangles of human body model and those of clothes for realistic simulation. Because the number of triangles is very large, the collision and reaction processing need a lot of time. To solve this problem, the proposed system decreases the number of collision and reaction processing by using the Octree space subdivision technique. It took a few seconds for generating a 3D human model putting on the designed 3D clothes.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.1
• /
• pp.33-38
• /
• 2006

In this paper, we propose implementation of 3D fashion show animation based on web which needs a construction of 3D fashion shopping mall. The 3D model made by 3D MAX program was exported XML type and displayed on web using ActiveX of D3D library. For the purpose of fashion show animation of 3D model in various clothes which selected by customer of shopping mall, we design the parts of standard clothes with hierarchical structure and assemble them. Next, we are mapping the various textures to them and animate 3D model in similar clothes which selected by customer on web.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.5
• /
• pp.229-236
• /
• 2023

Since 3D printed medical implant parts usually have surface defects, it is necessary to inspect the surface after manufacturing. In order to automate the surface inspection, it is effective to 3D scan the implant and reconstruct it as a scan model such as a point cloud. When constructing a scan model, the characteristics of the shape and material of the implant must be considered because it has characteristics different from those of general 3D printed parts. In this paper, we present a method to reconstruct the 3D scan model of a 3D printed metal bone-plate that is one kind of medical implant parts. Multiple partial scan data are produced by multi-view 3D scan, and then, we reconstruct a scan model by alignment and merging of partial data. We also present the process of the scan model reconstruction through experiments.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.7
• /
• pp.335-347
• /
• 2024

Open-vocabulary 3D point cloud instance segmentation (OV-3DIS) is a challenging visual task to segment a 3D scene point cloud into object instances of both base and novel classes. In this paper, we propose a novel model Open3DME for OV-3DIS to address important design issues and overcome limitations of the existing approaches. First, in order to improve the quality of class-agnostic 3D masks, our model makes use of T3DIS, an advanced Transformer-based 3D point cloud instance segmentation model, as mask proposal module. Second, in order to obtain semantically text-aligned visual features of each point cloud segment, our model extracts both 2D and 3D features from the point cloud and the corresponding multi-view RGB images by using pretrained CLIP and OpenSeg encoders respectively. Last, to effectively make use of both 2D and 3D visual features of each point cloud segment during label assignment, our model adopts a unique feature ensemble method. To validate our model, we conducted both quantitative and qualitative experiments on ScanNet-V2 benchmark dataset, demonstrating significant performance gains.

• Journal of Advanced Navigation Technology
• /
• v.13 no.1
• /
• pp.142-150
• /
• 2009

It is very important to generate a simplified model from a complex 3D character in computer game. We propose a new method of extracting feature lines from a 3D game character. Given an unstructured 3D character model containing texture information, we use model feature map (MFM), which is a 2D map that abstracts the variation of texture and curvature in the 3D character model. The MFM is created from both a texture map and a curvature map, which are produced separately by edge-detection to locate line features. The MFM can be edited interactively using standard image-processing tools. We demonstrate the technique on several data sets, including, but not limited to facial character.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.7
• /
• pp.881-891
• /
• 2020

In recent years, large-scale development of coastal areas has caused the loss of many lives and extensive property damage in coastal areas, due to wave overtopping caused by high-wave invasion and strong typhoons. However, coastal inundation studies considering the characteristics of domestic coastal areas are insufficient. This study is a methodology study that aimed to reproduce inundation of surge and wave complex elements by applying the ADCSWAN (ADCIRC+SWAN) and FLOW-3D models. In this study, the boundary data (sea level, wave) of the FLOW-3D model was extracted using the ADCSWAN (ADCIRC+SWAN) model and applied as the input value of the FLOW-3D model and a reproduction was created of the Flooding due to surge and overtopping in Busan Marine City when the typhoon Chaba passed. In addition, the existing overtopping empirical equation and the overtopping calculated by the FLOW-3D model were compared, and for coastal inundation, a qualitative verification was performed using the Inundation Trace Map of Land and Geospatial Informatrix Corporation, and the effectiveness of this study was reviewed.